© 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. 7093
    Prev
    Next
    INDEX
    Explanations

    man/woman, death, operation, fire, practice, living, value

    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
     kindness
    -0.09
     glory
    -0.09
     cherished
    -0.08
     kindly
    -0.08
     Glory
    -0.08
     majestic
    -0.08
     joy
    -0.08
     lighter
    -0.08
     purity
    -0.08
     excellence
    -0.08
    POSITIVE LOGITS
     sed
    0.13
    ầ
    0.11
     Marketable
    0.11
     Sed
    0.10
     lingerie
    0.10
     gyr
    0.10
    parm
    0.10
    -hot
    0.10
    vect
    0.10
     wid
    0.09
    Activations Density 0.015%

    No Known Activations