© 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. 32567
    Prev
    Next
    INDEX
    Explanations

    skin health and care

    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
    们
    -0.13
    们éĥ½
    -0.11
    ç°¸
    -0.10
    ses
    -0.09
    sert
    -0.09
    ess
    -0.09
    LLU
    -0.09
    们çļĦ
    -0.09
    颡
    -0.09
    ekt
    -0.09
    POSITIVE LOGITS
    çĬ¶åĨµ
    0.13
    çĭĢæ³ģ
    0.10
    ä»Ĺ
    0.10
    /he
    0.10
    æ·±å¤Ħ
    0.09
    è´¨éĩıåĴĮ
    0.09
    agem
    0.09
    ë§Ŀ
    0.09
    Õ¨
    0.09
     Ingram
    0.09
    Activations Density 0.013%

    No Known Activations