© 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. 4128
    Prev
    Next
    INDEX
    Explanations

    question answering formats

    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
    èĬ±
    -0.08
     cáo
    -0.08
    å¥ı
    -0.08
     Fit
    -0.07
    åijĬ
    -0.07
    伸åĩº
    -0.07
    inel
    -0.07
     symb
    -0.07
    rott
    -0.07
    Coder
    -0.07
    POSITIVE LOGITS
    åĹĴ
    0.11
    ç»ıéªĮåĴĮ
    0.11
    æĺ¯éĿŀ
    0.11
    é»ĺ
    0.11
    è¿ĻäºĽéĹ®é¢ĺ
    0.10
    ä¸Ģ项
    0.10
    两项
    0.10
    éĴ¦
    0.10
    çŃĶé¢ĺ
    0.10
    å¤ļ项
    0.09
    Activations Density 0.113%

    No Known Activations