© 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. 21929
    Prev
    Next
    INDEX
    Explanations

    contests and prizes

    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
    被åĬ¨
    -0.10
    使ä¹ĭ
    -0.09
    ernal
    -0.09
    _closure
    -0.08
     Commod
    -0.08
    æݨä»ĭä¼ļ
    -0.08
    æĥ¯
    -0.08
    åĤ¾
    -0.08
    让å®ĥ
    -0.08
    åı¯èĥ½åıijçĶŁ
    -0.08
    POSITIVE LOGITS
    -winning
    0.13
    è§ĦåĪĻ
    0.11
     prizes
    0.11
    éĢīæĭĶ
    0.11
    åİĨæŶ
    0.11
    ราà¸ĩ
    0.11
    zer
    0.10
    ç«ŀäºī
    0.10
    èĥľè´Ł
    0.10
    ä¸Ĭå²Ĺ
    0.10
    Activations Density 0.104%

    No Known Activations