© 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. 33308
    Prev
    Next
    INDEX
    Explanations

    keys in structured data

    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
    RelativeTo
    -0.07
    (getClass
    -0.07
     suede
    -0.07
     Rohing
    -0.07
    .easy
    -0.07
    ?>↵↵↵
    -0.07
    MinMax
    -0.06
    ComputedStyle
    -0.06
     lille
    -0.06
    .DEBUG
    -0.06
    POSITIVE LOGITS
    /foo
    0.08
     tempList
    0.08
    ,nil
    0.08
    úb
    0.08
    /effects
    0.08
     <%=
    0.07
    <small
    0.07
    ITERAL
    0.07
    ISIBLE
    0.07
     supposedly
    0.07
    Activations Density 17.900%

    No Known Activations