© 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. 92287
    Prev
    Next
    INDEX
    Explanations

    vision quest

    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
     Witnesses
    -0.09
    INGTON
    -0.09
    anna
    -0.09
     Pret
    -0.09
     sill
    -0.09
    ols
    -0.09
    Hur
    -0.08
    unga
    -0.08
     sensible
    -0.08
    cout
    -0.08
    POSITIVE LOGITS
    aries
    0.18
    naire
    0.14
    ary
    0.13
    arios
    0.13
     quests
    0.12
     quest
    0.12
    /audio
    0.11
    arias
    0.11
    quest
    0.11
     vision
    0.11
    Activations Density 0.018%

    No Known Activations