© 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. 13948
    Prev
    Next
    INDEX
    Explanations

    video or blog content

    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
     Dok
    -0.08
    abaj
    -0.08
     scape
    -0.07
     Gabriel
    -0.07
     Lamp
    -0.07
     Abel
    -0.07
     Dunk
    -0.07
     Pale
    -0.07
     Stones
    -0.07
    aram
    -0.07
    POSITIVE LOGITS
     Goose
    0.11
    arth
    0.11
     brokerage
    0.10
    aket
    0.10
    agos
    0.10
    ignment
    0.10
    dur
    0.10
     slugg
    0.10
    ramid
    0.10
    @dynamic
    0.10
    Activations Density 0.007%

    No Known Activations