© 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. 113279
    Prev
    Next
    INDEX
    Explanations

    division

    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
     semen
    -0.09
    Enlarge
    -0.09
     childish
    -0.08
    Piece
    -0.08
     far
    -0.08
    /assets
    -0.08
    orig
    -0.08
    undef
    -0.08
    Porno
    -0.08
     displ
    -0.08
    POSITIVE LOGITS
    ism
    0.12
    -friendly
    0.12
    isma
    0.11
    swith
    0.11
    ized
    0.11
    lla
    0.10
     friendly
    0.10
     prat
    0.10
    ischer
    0.10
     Populate
    0.10
    Activations Density 0.001%

    No Known Activations