© 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. 92612
    Prev
    Next
    INDEX
    Explanations

    curve fitting and shape analysis

    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
    Negative Logits
    s
    -0.11
    ersen
    -0.11
    wal
    -0.10
    nez
    -0.10
    arf
    -0.10
    lude
    -0.10
    naire
    -0.10
     Middleton
    -0.10
    /pm
    -0.10
    rec
    -0.10
    POSITIVE LOGITS
    ball
    0.12
    balls
    0.11
    aceous
    0.10
    ez
    0.09
    -shaped
    0.09
    yg
    0.09
    -lined
    0.08
    backs
    0.08
     nast
    0.08
    iness
    0.08
    Activations Density 0.020%

    No Known Activations