© 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. 49120
    Prev
    Next
    INDEX
    Explanations

    musicians' names

    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
    idel
    -0.11
    æµģæ°´
    -0.10
    沸èħ¾
    -0.08
    åľ¨çİ°åľº
    -0.08
    èĢģçĪ·
    -0.08
     Garr
    -0.08
    磬
    -0.08
    åħ¨æµģç¨ĭ
    -0.08
    èģ¿
    -0.08
    .Objects
    -0.08
    POSITIVE LOGITS
    æŃ»åIJİ
    0.16
    éĢĿä¸ĸ
    0.14
     died
    0.14
    åİ»ä¸ĸ
    0.13
    Dies
    0.13
    æŃ»äº¡
    0.13
     Dies
    0.13
    æŃ»èĢħ
    0.12
     Collapse
    0.12
    æ®ģ
    0.12
    Activations Density 0.106%

    No Known Activations