© 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. 33738
    Prev
    Next
    INDEX
    Explanations

    beginning activities / enabling actions

    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
    åĩºå¸Ńä¼ļè®®
    -0.09
    èĮ´
    -0.08
    æĹ¥å¸¸çĶŁæ´»
    -0.08
    åĪĽç«ĭ
    -0.08
    .Appearance
    -0.08
    .Attribute
    -0.08
    ë¡Ģ
    -0.08
    åıĤåĬłä¼ļè®®
    -0.08
    塬
    -0.08
    åºĬä¸Ĭ
    -0.08
    POSITIVE LOGITS
    ä½ĵéªĮ
    0.14
    é¢Ħ约
    0.12
    é«Ķé©Ĺ
    0.11
    åıĤä¸İèĢħ
    0.11
    åĻ¨æ¢°
    0.11
    çİ©æ³ķ
    0.10
    å½ĵ天
    0.10
    å®īåħ¨ä¿Ŀéļľ
    0.10
    票价
    0.10
    å½ĵæĹ¥
    0.10
    Activations Density 0.055%

    No Known Activations