© 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. 18107
    Prev
    Next
    INDEX
    Explanations

    numbers after tokens like `_`, `.git`, `Chapter`, `.`

    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
    eger
    -0.09
    ofi
    -0.09
    -held
    -0.09
    otos
    -0.09
    grade
    -0.09
    porto
    -0.09
    onso
    -0.09
    Drawable
    -0.08
    uzzi
    -0.08
    slide
    -0.08
    POSITIVE LOGITS
     ministers
    0.10
    iles
    0.10
     mort
    0.10
     fragment
    0.09
     merc
    0.09
     EXTRA
    0.09
    /questions
    0.09
    002
    0.08
    Defs
    0.08
    _mini
    0.08
    Activations Density 0.007%

    No Known Activations