© 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. 90763
    Prev
    Next
    INDEX
    Explanations

    note or notice

    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
     ma
    -0.09
    atsu
    -0.09
    享
    -0.09
    urat
    -0.09
    ulin
    -0.09
    Resp
    -0.09
    hell
    -0.08
     resp
    -0.08
    vu
    -0.08
    (from
    -0.08
    POSITIVE LOGITS
     note
    0.60
     Note
    0.46
    note
    0.43
    Note
    0.42
     NOTE
    0.37
     noteworthy
    0.34
    -note
    0.34
    NOTE
    0.32
    注æĦı
    0.32
     worth
    0.31
    Activations Density 0.660%

    No Known Activations