© 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. 25254
    Prev
    Next
    INDEX
    Explanations

    hood, time, names associated with it

    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
     reversible
    -0.09
     scanners
    -0.09
    arme
    -0.09
    blas
    -0.09
     trav
    -0.09
    ayan
    -0.09
     dire
    -0.08
     cil
    -0.08
     travelers
    -0.08
     abort
    -0.08
    POSITIVE LOGITS
     Hood
    0.12
    ijo
    0.11
    ESP
    0.10
     hood
    0.10
    esp
    0.09
     GIVEN
    0.09
    vern
    0.09
     Gord
    0.09
    prepend
    0.09
     withheld
    0.09
    Activations Density 0.001%

    No Known Activations