© 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. 15047
    Prev
    Next
    INDEX
    Explanations

    ( Chinese characters and names

    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
     Shops
    -0.09
     unpaid
    -0.08
    -s
    -0.08
     biochemical
    -0.08
     lain
    -0.07
    Kansas
    -0.07
    arton
    -0.07
     Downs
    -0.07
    atan
    -0.07
    icut
    -0.07
    POSITIVE LOGITS
     (?)
    0.12
     resp
    0.12
    µ¬
    0.11
    ró
    0.11
     lit
    0.11
     McGr
    0.10
     ??
    0.10
     disp
    0.10
     Resp
    0.09
    idl
    0.09
    Activations Density 0.309%

    No Known Activations