© 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. 25879
    Prev
    Next
    INDEX
    Explanations

    Kan, Han, ban

    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
     sag
    -0.10
    onom
    -0.10
     Wig
    -0.10
     Eb
    -0.09
     Sunrise
    -0.09
    som
    -0.09
    erk
    -0.08
    tok
    -0.08
     cuent
    -0.08
    su
    -0.08
    POSITIVE LOGITS
     toss
    0.12
    elda
    0.11
     bons
    0.11
    -worthy
    0.10
     Overs
    0.10
     patter
    0.10
     tossed
    0.10
     refrain
    0.09
     overs
    0.09
     simplicity
    0.09
    Activations Density 0.004%

    No Known Activations