© 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. 34193
    Prev
    Next
    INDEX
    Explanations

    skin color and complexion

    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
    çĩ§
    -0.10
    æĺİçıł
    -0.10
    ä¸į满
    -0.09
    åĨ²åĬ¨
    -0.09
    åIJĪçIJĨ
    -0.09
    lint
    -0.09
    ãĤ·ãĥ¼ãĤº
    -0.09
    ingu
    -0.09
    çĬ¯è§Ħ
    -0.09
    linger
    -0.08
    POSITIVE LOGITS
    èĦ¸èī²
    0.14
    èĭįçĻ½
    0.13
     pall
    0.11
    éĿ¢èī²
    0.11
     pale
    0.11
     Pall
    0.10
    åĨ·æ¼ł
    0.09
    arella
    0.09
     Komm
    0.09
    åĨ°åĨ·
    0.09
    Activations Density 0.039%

    No Known Activations