© 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. 6320
    Prev
    Next
    INDEX
    Explanations

    why questions

    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
    çĴł
    -0.10
    åĪ°åºķæĺ¯
    -0.10
    สà¸ĩ
    -0.09
    åij½åIJį
    -0.09
    .unknown
    -0.09
    çŃī诸å¤ļ
    -0.09
    éĥ½æĺ¯éĿŀ常
    -0.08
    remember
    -0.08
    ç©¿
    -0.08
    æºĥ
    -0.08
    POSITIVE LOGITS
    èĭĮ
    0.10
    ä¸įåłª
    0.09
    oundation
    0.09
    è¿Ļä¹Ī说
    0.09
    éĿŀåĩ¡
    0.09
    é¦Ĩ
    0.08
    èĩ»
    0.08
    治好
    0.08
    è¿Ļæł·è¯´
    0.08
    åĭĥ
    0.08
    Activations Density 0.196%

    No Known Activations