© 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. 2013
    Prev
    Next
    INDEX
    Explanations

    House of family or clan

    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
     Wagner
    -0.10
    æݪ
    -0.10
    chor
    -0.08
    褫
    -0.08
    ero
    -0.08
    raction
    -0.08
    äºĴèģĶäºĴéĢļ
    -0.08
    alytics
    -0.08
    èij
    -0.08
    æ¸Ķ
    -0.08
    POSITIVE LOGITS
    éķ¿è¿ľ
    0.10
    åľ¨é¦Ļ港
    0.10
    ä¸į足以
    0.09
    ä¸ĺ
    0.09
    éķ¿è¾Ī
    0.09
    __.__
    0.09
    оÑĢа
    0.09
    æ²Ļåıijä¸Ĭ
    0.09
    åľ¨å¤ĸ
    0.09
    çŁ¥åIJįåĵģçīĮ
    0.09
    Activations Density 0.109%

    No Known Activations