© 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. 36144
    Prev
    Next
    INDEX
    Explanations

    rising or falling noun

    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´²
    -0.09
    abilities
    -0.08
     comparatively
    -0.08
    è¡£
    -0.08
    ä¸į代表
    -0.07
    æĹ©æĹ©
    -0.07
    جÙĪ
    -0.07
    æĤ¨çļĦåŃ©åŃIJ
    -0.07
    å·²
    -0.07
    人为
    -0.07
    POSITIVE LOGITS
    ä¸Ģç¬Ķ
    0.11
    æĺ¯ä»ĸ
    0.10
    åĨĻçļĦ
    0.10
    å±±èĦī
    0.10
    olian
    0.09
    è¶
    0.09
    è¶ĭåĬ¿
    0.09
    ä¸ĩäºĭ
    0.09
    æĮ¤åİĭ
    0.09
    çļĦåİĭåĬĽ
    0.09
    Activations Density 0.082%

    No Known Activations