© 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. 61418
    Prev
    Next
    INDEX
    Explanations

    folk music and traditions

    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
    ãĥ³ãĤ°
    -0.09
    ãģĹãģ¦ãĤĤ
    -0.09
    ×Ļ׳×Ķ
    -0.09
    ãģĦãĤĭãģ¨
    -0.09
    _Base
    -0.08
    åħļçļĦé¢Ĩ导
    -0.08
    ugh
    -0.08
     Chin
    -0.08
     ÙĪغÙĬر
    -0.08
    ä¿ĺ
    -0.08
    POSITIVE LOGITS
    ings
    0.13
    lor
    0.12
    yled
    0.11
    媳
    0.11
    ãĢħ
    0.11
    çĽ¸ä¼ł
    0.10
    lore
    0.10
    iliar
    0.10
    ships
    0.10
    ../../../
    0.09
    Activations Density 0.032%

    No Known Activations