© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117219
    Prev
    Next
    INDEX
    Explanations

    computers, table, mountain

    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
     tremend
    -0.12
     -------↵
    -0.12
     fatt
    -0.12
    .AttributeSet
    -0.11
    agna
    -0.11
    Pdf
    -0.10
    _medium
    -0.10
    -neck
    -0.10
     Provincial
    -0.10
    chart
    -0.10
    POSITIVE LOGITS
     cafe
    0.07
     actress
    0.07
     prince
    0.07
     touchscreen
    0.07
     builders
    0.07
     HDC
    0.06
     ashes
    0.06
    ieg
    0.06
    .Expressions
    0.06
     decor
    0.06
    Activations Density 0.041%

    No Known Activations