© 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. 51319
    Prev
    Next
    INDEX
    Explanations

    interface with implementation

    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
    æĹ·
    -0.09
    鸳
    -0.08
    æĥħå¢ĥ
    -0.08
    综åIJĪæķ´æ²»
    -0.08
    æ·±åĪĩ
    -0.08
    鼷éľĨ
    -0.08
    èĤºçĤİ
    -0.08
    ieux
    -0.08
     Anc
    -0.08
    åħ¼
    -0.08
    POSITIVE LOGITS
    æİ¥åı£
    0.13
    interface
    0.11
     interface
    0.11
    çļĦä¸ĢéĿ¢
    0.11
    湫
    0.10
    çķĮéĿ¢
    0.10
    (interface
    0.10
    ä¸ĢéĿ¢
    0.10
    çļĦä¿¡å¿ĥ
    0.09
     Interface
    0.09
    Activations Density 0.327%

    No Known Activations