© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51503
    Prev
    Next
    INDEX
    Explanations

    sound and health conditions

    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
    éķľå¤´
    -0.09
    lord
    -0.08
    åĿ©
    -0.08
    çĽijäºĭä¼ļ
    -0.08
     Ends
    -0.08
    触
    -0.08
    iators
    -0.08
    å®ŀçī©
    -0.08
    ford
    -0.08
    _handling
    -0.07
    POSITIVE LOGITS
    æįĤ
    0.11
    æĺ¼
    0.10
    æĻ
    0.09
    æĤļ
    0.09
    åħ¬åħ±åľºæīĢ
    0.09
    ç¥Ł
    0.09
    æĮĩåIJij
    0.09
    ä¸Ĭ线
    0.08
    æºIJ头
    0.08
    å¤ķ
    0.08
    Activations Density 0.206%

    No Known Activations