© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19890
    Prev
    Next
    INDEX
    Explanations

    allow or permitted

    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
    embers
    -0.10
    ibu
    -0.10
     pageCount
    -0.09
    æĺ¾ç¤ºåĻ¨
    -0.09
    ingen
    -0.08
    arro
    -0.08
    纨
    -0.08
    å±ĭåŃIJ
    -0.08
    åĢ¼å¾Ĺä¸Ģ
    -0.08
    åħ¨åĽ½äººæ°ij
    -0.08
    POSITIVE LOGITS
    åĴĮæĶ¯æĮģ
    0.11
    许
    0.11
    è¿ĽæĿ¥
    0.10
    listed
    0.10
    scp
    0.10
    åħģ
    0.10
    éĢļè¡Į
    0.10
    許
    0.10
    ä¸Ģå®ļç¨ĭ度
    0.10
     permitted
    0.09
    Activations Density 0.058%

    No Known Activations