© 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. 14204
    Prev
    Next
    INDEX
    Explanations

    consists of

    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
     ver
    -0.12
    iat
    -0.11
    ughs
    -0.11
    ialis
    -0.11
     sympt
    -0.11
    aises
    -0.11
    logged
    -0.10
    achsen
    -0.10
    VS
    -0.10
     Stats
    -0.10
    POSITIVE LOGITS
     Zub
    0.09
     selv
    0.09
     mann
    0.08
    оÑĩ
    0.08
     fu
    0.07
    eec
    0.07
    미
    0.07
    reh
    0.07
     Brig
    0.07
    GOR
    0.07
    Activations Density 0.020%

    No Known Activations