© 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. 6985
    Prev
    Next
    INDEX
    Explanations

    end of clauses, punctuation endings

    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
    <|fim_middle|>
    -0.14
    ."č↵
    -0.11
    .↵↵↵
    -0.09
    <|fim_suffix|>
    -0.09
    issen
    -0.09
     (↵↵
    -0.08
    .↵↵↵↵↵↵↵↵↵↵↵↵
    -0.08
     EX
    -0.08
     Platz
    -0.08
     [...]↵↵
    -0.08
    POSITIVE LOGITS
    ,↵
    0.26
    ,/
    0.20
    ↵
    0.19
    ,//
    0.18
    ï¼Į↵
    0.17
     /
    0.16
     /↵
    0.16
    <br
    0.15
    ;/
    0.15
    /↵
    0.15
    Activations Density 0.513%

    No Known Activations