© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 28757
    Prev
    Next
    INDEX
    Explanations

    import; protected; ;

    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
     horny
    -0.11
     erot
    -0.09
     erotic
    -0.09
     bordel
    -0.08
    elic
    -0.08
     escap
    -0.08
     paradise
    -0.08
     undermin
    -0.08
     dames
    -0.08
     jeopard
    -0.08
    POSITIVE LOGITS
     MER
    0.11
     Clement
    0.10
     mer
    0.10
     Swe
    0.09
     .
    0.09
     Mer
    0.09
     Nie
    0.09
     Yong
    0.09
    éĢĢ
    0.09
     dual
    0.08
    Activations Density 0.106%

    No Known Activations