© 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. 14198
    Prev
    Next
    INDEX
    Explanations

    editing and polishing books

    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
    ambi
    -0.10
    ardi
    -0.09
    amba
    -0.09
     Rings
    -0.09
     alternatively
    -0.08
    ç«
    -0.08
     Stout
    -0.08
     modeling
    -0.08
    Fake
    -0.08
    pecified
    -0.08
    POSITIVE LOGITS
     polished
    0.18
     polish
    0.17
     cleaned
    0.15
     draft
    0.15
     drafts
    0.15
     readability
    0.15
     rough
    0.15
     manuscript
    0.14
     clean
    0.14
     grammar
    0.14
    Activations Density 0.152%

    No Known Activations