© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53245
    Prev
    Next
    INDEX
    Explanations

    (C) copyright symbol

    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
    ä»İä¸Ń
    -0.11
    ãģĻãģ¹
    -0.09
    ç¼ķ
    -0.09
    大åŀĭ
    -0.08
    èĵĿçīĻ
    -0.08
    欣
    -0.08
    Ñģл
    -0.08
    容
    -0.08
    ä½Ĩæĺ¯å¯¹äºİ
    -0.08
    御
    -0.08
    POSITIVE LOGITS
    venient
    0.09
     Duffy
    0.09
    åľ°æ®µ
    0.08
     Crom
    0.08
    çľĭä¸įè§ģ
    0.08
    ä¸Ģ件
    0.08
    设
    0.08
    âķ¯
    0.08
    ussen
    0.07
    éĢļ讯åijĺ
    0.07
    Activations Density 0.316%

    No Known Activations