© 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. 25282
    Prev
    Next
    INDEX
    Explanations

    self-assembly, own breed

    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
    tern
    -0.08
     gaz
    -0.08
     ongoing
    -0.08
    atto
    -0.07
     general
    -0.07
     Toolbox
    -0.07
     cra
    -0.07
    urr
    -0.07
    elm
    -0.07
     stranger
    -0.07
    POSITIVE LOGITS
    /original
    0.11
    /team
    0.11
    ACP
    0.11
    .avi
    0.11
    cest
    0.11
    ILLA
    0.10
    lesh
    0.10
    /by
    0.10
    igne
    0.10
    uko
    0.10
    Activations Density 0.060%

    No Known Activations