© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57351
    Prev
    Next
    INDEX
    Explanations

    dry skin and hair

    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¨Ģè¡Į
    -0.11
    æĢĢçĿĢ
    -0.10
    å½ĵå¹´
    -0.10
    æ§Ł
    -0.09
     licensors
    -0.09
    åħ¬å¹³
    -0.09
    oze
    -0.09
    ableObject
    -0.09
    æŃª
    -0.09
    蹶
    -0.08
    POSITIVE LOGITS
    ä¿Ŀ湿
    0.11
    æ»ĭ润
    0.10
    è®®
    0.10
    abo
    0.09
     Cohen
    0.09
    æĹłåı¯
    0.08
    è¾ĩ
    0.08
     Franc
    0.08
    èij£
    0.08
    æ·¦
    0.08
    Activations Density 0.058%

    No Known Activations