© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48596
    Prev
    Next
    INDEX
    Explanations

    py- words

    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
    ellig
    -0.10
    weit
    -0.10
    è®°
    -0.10
     Epid
    -0.09
    /trans
    -0.09
     Legisl
    -0.09
    pac
    -0.09
     Wings
    -0.09
     rep
    -0.09
    conte
    -0.09
    POSITIVE LOGITS
    thag
    0.15
    ramids
    0.14
    ramid
    0.13
    gments
    0.12
     py
    0.12
    dna
    0.11
    htag
    0.11
    gment
    0.10
    charm
    0.10
    ongyang
    0.10
    Activations Density 0.113%

    No Known Activations