© 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. 26251
    Prev
    Next
    INDEX
    Explanations

    . or non-word punctuation

    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
    *↵
    -0.09
     :↵
    -0.09
     Dor
    -0.08
    <|fim_middle|>
    -0.08
    -↵
    -0.08
     Dias
    -0.08
     intercept
    -0.08
     Zag
    -0.08
     Croat
    -0.08
    Âł↵
    -0.08
    POSITIVE LOGITS
     ·
    0.14
    âĢİ
    0.14
     ...
    0.14
     Jul
    0.14
     [].
    0.14
    ::.
    0.12
    :.
    0.12
     Sep
    0.12
    Feb
    0.12
     ().
    0.12
    Activations Density 0.474%

    No Known Activations