© 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. 25238
    Prev
    Next
    INDEX
    Explanations

    follow us on social media or app

    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
    aran
    -0.09
     gag
    -0.08
     Arabian
    -0.08
    Selector
    -0.07
     sparse
    -0.07
     peek
    -0.07
    zel
    -0.07
     GENERIC
    -0.07
    IFE
    -0.07
    afil
    -0.07
    POSITIVE LOGITS
     {?}
    0.12
     Geography
    0.10
    parm
    0.10
    Follow
    0.10
     Bis
    0.10
     FB
    0.10
     Kin
    0.10
     fb
    0.10
     slur
    0.10
     kin
    0.10
    Activations Density 0.002%

    No Known Activations