© 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. 3806
    Prev
    Next
    INDEX
    Explanations

    family and friends

    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
     thereof
    -0.09
     plac
    -0.08
     ten
    -0.08
    /oct
    -0.08
     Yad
    -0.08
     dess
    -0.08
     tres
    -0.08
    xc
    -0.08
    /ag
    -0.07
    話
    -0.07
    POSITIVE LOGITS
     kids
    0.12
     folks
    0.11
     kino
    0.11
     guys
    0.11
    olini
    0.10
     kidd
    0.10
     biz
    0.10
     ol
    0.10
    ieber
    0.10
    kids
    0.10
    Activations Density 0.174%

    No Known Activations