© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 6596
    Prev
    Next
    INDEX
    Explanations

    money, fate, folly, advertised, months

    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
    <|endoftext|>
    -0.17
    <|fim_middle|>
    -0.13
    ){}↵
    -0.13
    oub
    -0.12
    );↵
    -0.12
     exhausting
    -0.11
     Liv
    -0.11
     Shade
    -0.11
    ;↵
    -0.11
    )↵
    -0.11
    POSITIVE LOGITS
    .Here
    0.17
    —and
    0.16
     [â̦]↵↵
    0.15
    .First
    0.14
    —or
    0.13
    —but
    0.12
    â̦↵↵
    0.12
    .EXP
    0.11
     —
    0.11
    —at
    0.11
    Activations Density 3.675%

    No Known Activations