© 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. 48297
    Prev
    Next
    INDEX
    Explanations

    script execution

    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
    ведиÑĤе
    -0.13
    łĢ
    -0.10
    ContentLoaded
    -0.09
    TRS
    -0.09
    oit
    -0.09
    svm
    -0.08
    ìĦ¸ìļĶ
    -0.08
     Tie
    -0.08
    owing
    -0.08
    phans
    -0.08
    POSITIVE LOGITS
    adays
    0.21
    etheless
    0.21
    gether
    0.20
    xiety
    0.17
    greSQL
    0.16
    tempts
    0.13
    rition
    0.13
    bsites
    0.13
    quarters
    0.13
    struments
    0.12
    Activations Density 2.205%

    No Known Activations