© 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. 38793
    Prev
    Next
    INDEX
    Explanations

    whole story or complete

    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
    æĶ¶åĽŀ
    -0.08
    注æĺİæĿ¥æºIJ
    -0.08
    群
    -0.08
    ä¼ĺæĥłæĶ¿çŃĸ
    -0.08
    iso
    -0.08
    æĮģç»Ńæİ¨è¿Ľ
    -0.08
    apo
    -0.08
    ì°©
    -0.08
    ån
    -0.08
    æī§è¡ĮåĬĽ
    -0.08
    POSITIVE LOGITS
    å®Įæķ´
    0.14
    å®Įæķ´çļĦ
    0.12
    羣缸
    0.12
     incomplete
    0.11
     complete
    0.11
    æ¯Ķäºļ
    0.10
    COMPLETE
    0.10
     erm
    0.10
    åħ¨éĿ¢
    0.10
    åı¦ä¸Ģè¾¹
    0.09
    Activations Density 0.045%

    No Known Activations