© 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. 57666
    Prev
    Next
    INDEX
    Explanations

    I need, solution, exercise

    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
    åIJİèĢħ
    -0.08
     alf
    -0.08
    uml
    -0.08
     DISCLAIMER
    -0.07
    REFERRED
    -0.07
    éĺķ
    -0.07
    æݨæµĭ
    -0.07
    LER
    -0.07
    Crime
    -0.07
    hei
    -0.07
    POSITIVE LOGITS
    使çĶ¨ç¶²è·¯
    0.09
    ç¬ijç¬ij
    0.09
    é¢ĺ缮
    0.09
    çķĮ第ä¸Ģ
    0.08
    ç½ijç«Ļåľ°åĽ¾
    0.08
    spo
    0.08
    ä¿Ŀä½ı
    0.08
    çĮ©
    0.08
    请æĤ¨
    0.08
    Contained
    0.08
    Activations Density 0.862%

    No Known Activations