© 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. 50949
    Prev
    Next
    INDEX
    Explanations

    most surely know

    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
     Abbott
    -0.09
     privileges
    -0.09
    ledge
    -0.09
     Nin
    -0.09
     gre
    -0.08
    ice
    -0.08
     unp
    -0.08
     dirty
    -0.08
    ÑĤÑĮ
    -0.08
     Comm
    -0.08
    POSITIVE LOGITS
    erner
    0.11
    fov
    0.10
     jud
    0.10
     minded
    0.10
    DY
    0.10
    _OVER
    0.10
     Cout
    0.09
    -inverse
    0.09
    Divider
    0.09
    awai
    0.09
    Activations Density 0.051%

    No Known Activations