© 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. 25309
    Prev
    Next
    INDEX
    Explanations

    muscle and muscular terms

    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
     plaint
    -0.10
     Whit
    -0.10
     explic
    -0.10
     Barnes
    -0.10
     simpl
    -0.10
     guar
    -0.09
     pint
    -0.09
     Loft
    -0.09
     crowds
    -0.09
     Blond
    -0.09
    POSITIVE LOGITS
     Ske
    0.09
    obia
    0.09
     Ruth
    0.09
     denen
    0.09
    Ñĥг
    0.08
     pronounce
    0.08
    etty
    0.08
    cheng
    0.08
    uzz
    0.08
    pollo
    0.08
    Activations Density 0.003%

    No Known Activations