© 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. 8492
    Prev
    Next
    INDEX
    Explanations

    hair and its growth

    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
    è¹ĭ
    -0.11
    phem
    -0.10
    å®ī举
    -0.10
    ERR
    -0.10
    å®īåħ¨æĢ§
    -0.09
    åĸĩåıŃ
    -0.09
    atel
    -0.08
    æĿijå§Ķä¼ļ
    -0.08
    Outlet
    -0.08
    PRICE
    -0.08
    POSITIVE LOGITS
    头åıij
    0.22
     hair
    0.19
     волоÑģ
    0.17
    hair
    0.17
    Hair
    0.17
     Hair
    0.17
    èĦ±åıij
    0.16
    ç§ĥ
    0.15
     haired
    0.14
    é«®
    0.14
    Activations Density 0.118%

    No Known Activations