© 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. 3664
    Prev
    Next
    INDEX
    Explanations

    gut related words and names

    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
    hood
    -0.11
    iffe
    -0.10
    izable
    -0.10
    href
    -0.10
    ultip
    -0.10
    essa
    -0.10
     Worst
    -0.10
    GROUND
    -0.09
    alez
    -0.09
    hower
    -0.09
    POSITIVE LOGITS
    ierrez
    0.19
    ters
    0.18
    ted
    0.16
    ting
    0.14
    tatus
    0.13
     wrench
    0.13
    ta
    0.12
    tridge
    0.11
    achten
    0.11
    ty
    0.11
    Activations Density 0.018%

    No Known Activations