© 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. 17924
    Prev
    Next
    INDEX
    Explanations

    plans changed or canceled

    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
    åľĨ满å®ĮæĪIJ
    -0.09
    uras
    -0.09
    çģĮ
    -0.09
    TokenType
    -0.08
    éģĭçĶ¨
    -0.08
    atrix
    -0.08
    è¿°èģĮ
    -0.08
    è¿ĩ渡
    -0.08
    亲
    -0.08
    åľ¨è¿ĩæ¸¡æľŁ
    -0.08
    POSITIVE LOGITS
    åıĸæ¶Ī
    0.11
    åı£å¾Ħ
    0.10
    åİŁæĿ¥çļĦ
    0.10
    æµģ产
    0.10
    åİŁåħĪ
    0.10
    åİŁä¾Ĩ
    0.10
    åİŁæľ¬
    0.10
    åİŁæĿ¥
    0.10
     originally
    0.10
    å¤Ń
    0.10
    Activations Density 0.115%

    No Known Activations