© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26517
    Prev
    Next
    INDEX
    Explanations

    look, reflect, search, evaluate, try

    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
     unknow
    -0.15
     Somehow
    -0.12
     somehow
    -0.11
    /goto
    -0.11
     proving
    -0.11
    ogl
    -0.11
    åijĬ
    -0.10
     Erect
    -0.10
    afort
    -0.10
     Castro
    -0.10
    POSITIVE LOGITS
     observing
    0.15
     look
    0.15
     reading
    0.15
     noting
    0.14
     attent
    0.14
     Look
    0.14
     looking
    0.13
     jot
    0.13
     paying
    0.13
    Look
    0.12
    Activations Density 0.074%

    No Known Activations