© 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. 49007
    Prev
    Next
    INDEX
    Explanations

    in accordance

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     stead
    -0.13
     Uhr
    -0.13
    EMP
    -0.12
    709
    -0.11
    her
    -0.11
     Gomez
    -0.11
    tk
    -0.11
    ales
    -0.11
     emp
    -0.11
    909
    -0.11
    POSITIVE LOGITS
    -depth
    0.07
    oga
    0.07
    Existing
    0.06
     Patrol
    0.06
    Brun
    0.06
    avax
    0.06
     drunk
    0.06
     Existing
    0.06
     Patricia
    0.06
     bumper
    0.06
    Activations Density 0.066%

    No Known Activations