© 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. 90590
    Prev
    Next
    INDEX
    Explanations

    Corning grip of terror

    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
     Lic
    -0.11
    iras
    -0.11
     oy
    -0.10
     Piper
    -0.10
     lic
    -0.10
    Lic
    -0.09
     Damon
    -0.09
    ToLeft
    -0.09
     dam
    -0.09
    emm
    -0.09
    POSITIVE LOGITS
     Loft
    0.10
     bureaucr
    0.09
    reau
    0.09
     '
    0.08
     indeed
    0.08
     Ville
    0.08
    ç½®
    0.08
     expl
    0.08
    lep
    0.08
    le
    0.08
    Activations Density 0.002%

    No Known Activations