© 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. 29021
    Prev
    Next
    INDEX
    Explanations

    forwarded by Enron ETC

    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
    âĢ¦and
    -0.10
    [âĢ¦
    -0.09
    emma
    -0.09
    QObject
    -0.09
    ,set
    -0.09
    .pivot
    -0.09
    oco
    -0.09
     belang
    -0.09
    ilyn
    -0.08
     Truly
    -0.08
    POSITIVE LOGITS
     etc
    0.13
    etc
    0.10
    zan
    0.09
     aust
    0.09
     _č↵
    0.09
    itized
    0.09
    acher
    0.09
    uner
    0.08
    elden
    0.08
    à¹Į
    0.08
    Activations Density 0.415%

    No Known Activations