© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39701
    Prev
    Next
    INDEX
    Explanations

    Scout Executive, Scouting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_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
    çłĶ究éĻ¢
    -0.09
    Stroke
    -0.09
     Stroke
    -0.09
    ç´¯äºĨ
    -0.08
     Cage
    -0.08
    æ¡Ĩ
    -0.08
    æ§Ľ
    -0.08
    stroke
    -0.08
     stroke
    -0.08
    .datab
    -0.08
    POSITIVE LOGITS
     Scout
    0.12
     Scouts
    0.10
    å·¥
    0.10
    dio
    0.10
     scout
    0.10
    åѦåĪ°
    0.09
     scouts
    0.09
    丼æŀĹ
    0.09
    èļģ
    0.09
     па
    0.09
    Activations Density 0.036%

    No Known Activations