© 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. 38001
    Prev
    Next
    INDEX
    Explanations

    contacting or asking

    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
    åŀĥ
    -0.08
    atan
    -0.08
    ä¸Ģæīĭ
    -0.08
    enumer
    -0.08
    æĸ°äº§åĵģ
    -0.07
    3
    -0.07
    1
    -0.07
    èĤĺ
    -0.07
    Misc
    -0.07
    çī©åĵģ
    -0.07
    POSITIVE LOGITS
    æľīåħ³éĥ¨éŨ
    0.12
    请æķĻ
    0.11
    åĴ¨è¯¢
    0.11
    缸åħ³éĥ¨éŨ
    0.11
    çĵ£
    0.11
    ä¸ĭ游
    0.11
    第ä¸īæĸ¹
    0.11
    ä¸ĵ家
    0.10
    çļĦä¸ĵä¸ļ
    0.10
    alion
    0.10
    Activations Density 0.170%

    No Known Activations