© 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. 35300
    Prev
    Next
    INDEX
    Explanations

    full descriptor

    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
    主åĬ¨æĢ§
    -0.10
     ÑĥнивеÑĢÑģ
    -0.09
    /storage
    -0.09
    cus
    -0.09
    å®Įç¾İ
    -0.09
    rego
    -0.09
    ä»İ容
    -0.08
    боÑĤ
    -0.08
    anness
    -0.08
    士
    -0.08
    POSITIVE LOGITS
    åı£è¢ĭ
    0.09
     rem
    0.09
    æİ¥éĢģ
    0.08
    äºĮç»´
    0.08
    æľĽåİ»
    0.08
    éĩıåĮĸ
    0.08
    çļĦä¸ĢåĪĩ
    0.08
    æĹĮ
    0.08
    æĽ´ä½ķåĨµ
    0.08
    ç±»åŀĭçļĦ
    0.08
    Activations Density 0.019%

    No Known Activations