© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115143
    Prev
    Next
    INDEX
    Explanations

    code formatting and symbols

    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
     MAK
    -0.11
    osa
    -0.11
    shint
    -0.09
     Spinner
    -0.09
     rejo
    -0.09
     guessed
    -0.09
    jem
    -0.09
     unprotected
    -0.08
     fre
    -0.08
    uset
    -0.08
    POSITIVE LOGITS
     *"
    0.10
     Boom
    0.10
     "..
    0.10
     flash
    0.09
     "...
    0.09
     FLASH
    0.09
    FLASH
    0.09
    bjerg
    0.09
    <|fim_suffix|>
    0.08
    ave
    0.08
    Activations Density 0.021%

    No Known Activations