© 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. 8286
    Prev
    Next
    INDEX
    Explanations

    delivery service

    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
    Negative Logits
    immers
    -0.09
     Fors
    -0.08
     scrambling
    -0.08
     exclus
    -0.08
     Crystal
    -0.08
     acqu
    -0.08
     exclusive
    -0.08
     Phillips
    -0.08
     fors
    -0.08
     habit
    -0.08
    POSITIVE LOGITS
     unaffected
    0.10
    cke
    0.10
     rims
    0.10
     Cornwall
    0.10
     Kear
    0.10
    egis
    0.10
    .*(
    0.10
    hra
    0.10
     Picks
    0.10
     Priority
    0.10
    Activations Density 0.040%

    No Known Activations