© 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. 16083
    Prev
    Next
    INDEX
    Explanations

    is are functions free

    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
    roz
    -0.10
     Ou
    -0.09
     bang
    -0.09
     adm
    -0.09
     Borg
    -0.09
     banging
    -0.09
    Wo
    -0.09
    ì§
    -0.09
     apprec
    -0.09
     Brotherhood
    -0.09
    POSITIVE LOGITS
     beautiful
    0.18
     beaut
    0.14
    beautiful
    0.14
     gorgeous
    0.14
     Beautiful
    0.13
     beauty
    0.12
    unter
    0.11
     Gorgeous
    0.11
    Tyler
    0.11
    Beautiful
    0.10
    Activations Density 0.007%

    No Known Activations