© 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. 32837
    Prev
    Next
    INDEX
    Explanations

    hair dye treatments and products

    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
    æ¢Ń
    -0.10
    æݬ
    -0.09
    æºħ
    -0.08
    è¿Ľè´§
    -0.08
    è¯Ļ
    -0.08
    inux
    -0.08
    èĨ¨èĥĢ
    -0.08
    ì¶ķ
    -0.08
    åĹĵ
    -0.08
    è´²
    -0.08
    POSITIVE LOGITS
    ç»ı纪人
    0.10
    ibal
    0.09
    ç»ı纪
    0.09
    ä¾µåįł
    0.09
    å¤ļå¤ļ
    0.08
    ÑĤÑıж
    0.08
    ÙĤØ·
    0.08
    hel
    0.08
    çīºçī²
    0.08
    ä¸Ģéģĵ
    0.08
    Activations Density 0.081%

    No Known Activations