© 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. 112192
    Prev
    Next
    INDEX
    Explanations

    draw attention to something

    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
     Cher
    -0.11
    piel
    -0.09
     regrets
    -0.09
     Quarter
    -0.09
     persever
    -0.09
    odu
    -0.09
    sein
    -0.09
    qus
    -0.09
     ment
    -0.08
     blame
    -0.08
    POSITIVE LOGITS
     look
    0.19
    Look
    0.18
     Look
    0.17
    look
    0.15
    LOOK
    0.14
     LOOK
    0.14
     Come
    0.13
     check
    0.13
    Check
    0.13
     listen
    0.13
    Activations Density 0.057%

    No Known Activations