© 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. 91987
    Prev
    Next
    INDEX
    Explanations

    American History, Milton Freewater, Jewelry Boxes

    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
    atted
    -0.12
    oti
    -0.12
    Erot
    -0.11
     especial
    -0.11
     penetrating
    -0.11
    ologically
    -0.11
     =",
    -0.11
    icode
    -0.11
    igner
    -0.11
    azers
    -0.11
    POSITIVE LOGITS
    <|endoftext|>
    0.16
    âĢİ
    0.10
     thems
    0.07
     .↵↵↵↵
    0.06
    -live
    0.06
    ,eg
    0.06
     dess
    0.06
     (/
    0.06
     stor
    0.06
    ".↵↵↵↵
    0.05
    Activations Density 1.021%

    No Known Activations