© 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. 35701
    Prev
    Next
    INDEX
    Explanations

    energy projectiles and weapons

    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
    å½ĵæĹ¥
    -0.08
    åķ»
    -0.08
    æīª
    -0.08
    沦为
    -0.08
    å®īéĿĻ
    -0.08
    åģļ梦
    -0.08
    è¾¹çķĮ
    -0.07
     immortal
    -0.07
    ä¸ĢæĹ¥
    -0.07
    èĪĮ头
    -0.07
    POSITIVE LOGITS
    æĭĸ延
    0.11
    ç²¾åĩĨ
    0.10
    ä¸į容
    0.09
    _DL
    0.09
    åĩĿèģļ
    0.09
    æ´º
    0.09
    åľ°éģĵ
    0.09
    åı¤ä»Ĭ
    0.09
    åIJĮæł·æĺ¯
    0.09
    æŀĦçŃij
    0.08
    Activations Density 0.032%

    No Known Activations