© 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. 35348
    Prev
    Next
    INDEX
    Explanations

    eating veggies

    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
    è¿Ļæł·çļĦ
    -0.10
    è¿Ļç±»
    -0.10
    нÑĭ
    -0.10
    è¿Ļ款游æĪı
    -0.10
    æľīè¿Ļæł·çļĦ
    -0.09
     xPos
    -0.09
    è¿ĻéĩĮçļĦ
    -0.09
    è¿ĻéĩĮæľī
    -0.09
    è¿Ļ段
    -0.09
    è¿Ļæł·ä¸Ģ个
    -0.09
    POSITIVE LOGITS
     pes
    0.11
    åı¯ä¸įæĺ¯
    0.09
    ÑĥÑĪ
    0.09
    olem
    0.09
    åĽŀäºĭ
    0.08
    çľĭä¼¼
    0.08
    ledo
    0.08
    è¿ĺæĥ³
    0.08
    æ³ī
    0.08
    æıIJåĪ°
    0.08
    Activations Density 0.062%

    No Known Activations