© 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. 14552
    Prev
    Next
    INDEX
    Explanations

    code.com

    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
    .edu
    -0.10
    osate
    -0.10
    (typ
    -0.09
     ****
    -0.09
    <tbody
    -0.09
    lica
    -0.09
    itant
    -0.09
    (Collectors
    -0.09
     fabs
    -0.09
    pec
    -0.09
    POSITIVE LOGITS
    lijah
    0.08
    )[:
    0.07
    WRAPPER
    0.07
     flashy
    0.07
     BLL
    0.07
    Deserializer
    0.07
    ¦¬
    0.07
    @Web
    0.07
    Ĭ
    0.06
    strcasecmp
    0.06
    Activations Density 2.552%

    No Known Activations