© 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. 17358
    Prev
    Next
    INDEX
    Explanations

    "i have", "pay attention", "publish in"

    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
    çľĭæ¸ħ
    -0.08
    æ¤IJ
    -0.08
     Sith
    -0.08
    èĻ¿
    -0.08
    æĬĹçĸ«
    -0.08
    绿水
    -0.08
    åħ¥åºĵ
    -0.08
    åijĺ
    -0.08
    ä¸ĩéĩĮ
    -0.07
    åĮł
    -0.07
    POSITIVE LOGITS
    对èĩªå·±
    0.08
    ä»Ĩ
    0.08
    æĬij
    0.08
    ipi
    0.08
    psc
    0.08
    olio
    0.08
    _reviews
    0.08
    ÙħÙĪس
    0.07
    /uploads
    0.07
    /pg
    0.07
    Activations Density 0.445%

    No Known Activations