© 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. 23377
    Prev
    Next
    INDEX
    Explanations

    hit songs

    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
    ÙĬات
    -0.09
    åĨĻçļĦ
    -0.09
    è¾Ľèĭ¦
    -0.09
    anse
    -0.09
    hips
    -0.09
    ities
    -0.08
    纯æ´ģ
    -0.08
    ãģĦãĤĭ
    -0.07
    sexual
    -0.07
    itional
    -0.07
    POSITIVE LOGITS
     ÑģпÑĢав
    0.10
    èĢIJ磨
    0.10
    uiltin
    0.09
    ulen
    0.09
    LookAndFeel
    0.09
    è¤IJ
    0.09
    ernel
    0.09
    们
    0.08
    arness
    0.08
    æł¡å¤ĸ
    0.08
    Activations Density 0.011%

    No Known Activations