© 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. 112617
    Prev
    Next
    INDEX
    Explanations

    no, more, or and

    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
    xico
    -0.08
     algun
    -0.08
    uin
    -0.08
     deb
    -0.08
    âĢ¦the
    -0.08
    memberof
    -0.08
    .forEach
    -0.08
     annon
    -0.08
     numerous
    -0.08
    roit
    -0.08
    POSITIVE LOGITS
     Ding
    0.11
    lez
    0.10
    ulla
    0.10
    .tem
    0.09
     Vill
    0.09
     Aval
    0.09
     Brom
    0.09
    ror
    0.09
     Thi
    0.09
    eded
    0.09
    Activations Density 0.106%

    No Known Activations