© 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. 5003
    Prev
    Next
    INDEX
    Explanations

    such as

    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
    aleb
    -0.10
    çļĦä¸Ģ个
    -0.09
    åı¤äºº
    -0.09
    æĢ¯
    -0.08
    å½ĵåľ°æŶéĹ´
    -0.08
    ä¹Łè®¸æĺ¯
    -0.08
    举åĬŀçļĦ
    -0.08
    enstein
    -0.08
    edu
    -0.08
    ä¸ĢçĻ¾
    -0.08
    POSITIVE LOGITS
    æ±ī
    0.08
    享åıĹ
    0.08
    让æĪij们
    0.08
    许
    0.08
    hip
    0.08
    寡
    0.08
     McGr
    0.08
    æ¢Ń
    0.08
    ual
    0.08
    åĥı
    0.08
    Activations Density 0.087%

    No Known Activations