© 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. 18729
    Prev
    Next
    INDEX
    Explanations

    small amount 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
    Negative Logits
     somewhat
    -0.13
    jom
    -0.11
    cdb
    -0.11
    avs
    -0.11
     pornos
    -0.11
    irs
    -0.11
     glands
    -0.10
    oui
    -0.10
    Gap
    -0.10
     awhile
    -0.10
    POSITIVE LOGITS
     (<
    0.12
     (~
    0.11
    ingly
    0.10
     extra
    0.10
    /stdc
    0.10
     amount
    0.09
     (.
    0.09
    -town
    0.09
     amounts
    0.08
     spice
    0.08
    Activations Density 0.018%

    No Known Activations