© 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. 34592
    Prev
    Next
    INDEX
    Explanations

    crash into, drop down, set out

    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
    è¿ĻæĿ¡è·¯
    -0.09
    æ³īæ°´
    -0.09
     Gallagher
    -0.08
    è¹ij
    -0.08
    åŃĶéĽĢ
    -0.08
    鸢
    -0.08
    è¿Ļ段
    -0.08
    ä¸ĢæŶ
    -0.08
    åĨł
    -0.08
    èģªæĺİ
    -0.08
    POSITIVE LOGITS
    ä¸į容
    0.11
    æģ«
    0.10
    ARTH
    0.09
    æij§æ¯ģ
    0.09
    æ°¸ä¸į
    0.09
    éĻį临
    0.09
    人类
    0.09
    巨大
    0.09
    jure
    0.09
    主人
    0.09
    Activations Density 0.057%

    No Known Activations