© 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. 113828
    Prev
    Next
    INDEX
    Explanations

    show, showing, showed

    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
    .shtml
    -0.10
    Won
    -0.10
    nown
    -0.10
    ikon
    -0.10
     owing
    -0.10
     caught
    -0.10
     Caught
    -0.09
    lator
    -0.09
    orado
    -0.09
    licken
    -0.09
    POSITIVE LOGITS
     off
    0.19
    -off
    0.14
     why
    0.13
    off
    0.13
     restraint
    0.12
     how
    0.11
     everyone
    0.11
     Off
    0.11
     that
    0.10
    _off
    0.10
    Activations Density 0.024%

    No Known Activations