© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31782
    Prev
    Next
    INDEX
    Explanations

    lookup and tracing records

    np_acts-logits-general · gemini-2.5-flash-lite

    technical documentation and reference material containing specific details, numbers, and procedural information.

    oai_token-act-pair · claude-4-5-haikuTriggered by @cam

    lookup

    np_max-act-logits · claude-4-5-haikuTriggered by @cam
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lad
    -0.12
     Muse
    -0.11
     commod
    -0.10
     vouchers
    -0.10
     Commod
    -0.10
     Forbidden
    -0.09
     Hut
    -0.09
     labyrinth
    -0.09
    subcategory
    -0.09
     muse
    -0.09
    POSITIVE LOGITS
     lookup
    0.20
    Lookup
    0.19
     Lookup
    0.19
     reverse
    0.17
    lookup
    0.16
     tracing
    0.16
     traced
    0.15
     trace
    0.15
     records
    0.15
    å§ĵåIJį
    0.15
    Activations Density 0.269%

    No Known Activations