© 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. 32551
    Prev
    Next
    INDEX
    Explanations

    hair treatment and conditioning

    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
    çļ®èĤ¤
    -0.09
    æĪ³
    -0.08
    mast
    -0.08
    驼
    -0.08
    acio
    -0.08
     Ñģка
    -0.08
    æ§Ĭ
    -0.08
     mast
    -0.08
    è¢ľ
    -0.08
    Peak
    -0.08
    POSITIVE LOGITS
    ç»ĵæŀĦæĢ§
    0.10
    çĵ®
    0.10
    akh
    0.09
    漫éķ¿çļĦ
    0.09
    _HAL
    0.09
    åħ¬ç¤¾
    0.08
    éķ¿æľŁ
    0.08
    çĦĹ
    0.08
     Stout
    0.08
    ä¿Ŀä½ı
    0.08
    Activations Density 0.050%

    No Known Activations