© 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. 58591
    Prev
    Next
    INDEX
    Explanations

    film fund, reminders, rates apply

    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
    è´°
    -0.09
    èį¡
    -0.09
    éĽĨåĽ¢èĤ¡ä»½
    -0.08
    èĥ¶
    -0.08
    äºĨä¸ĭæĿ¥
    -0.08
    èĨł
    -0.08
    çĽ
    -0.08
    hips
    -0.08
    çļĦæķĪæŀľ
    -0.08
    rot
    -0.08
    POSITIVE LOGITS
    ç´¢åıĸ
    0.09
    ä¸įèī¯ä¿¡æģ¯
    0.09
    工信éĥ¨
    0.08
    ç¯ĵ
    0.08
    Imm
    0.08
    ï¹¢
    0.08
    oods
    0.08
    ä»»ä½ķä¸Ģ个
    0.08
    -handler
    0.08
     nab
    0.08
    Activations Density 0.006%

    No Known Activations