© 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. 7964
    Prev
    Next
    INDEX
    Explanations

    is/was/has been followed by indicating state or confirmation

    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
     ones
    -0.11
    kop
    -0.10
     Carn
    -0.10
    atas
    -0.10
    /if
    -0.09
     punct
    -0.09
     Aussie
    -0.09
     disposition
    -0.09
    ICC
    -0.09
    nette
    -0.09
    POSITIVE LOGITS
     pity
    0.15
     compulsory
    0.12
     obligatory
    0.11
     privilege
    0.11
     shame
    0.10
     mandatory
    0.10
     Liberation
    0.10
     indeed
    0.10
     вÑĢемÑı
    0.10
     evident
    0.10
    Activations Density 0.132%

    No Known Activations