© 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. 31813
    Prev
    Next
    INDEX
    Explanations

    vehicle handling control

    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
     ÑĥÑģл
    -0.09
     adam
    -0.09
     Choir
    -0.09
    èĴ¸
    -0.09
     Reform
    -0.08
     reform
    -0.08
    稿
    -0.08
    èĥĮä¸Ĭ
    -0.08
    æĶ¹éĿ©
    -0.08
    5
    -0.08
    POSITIVE LOGITS
    çĭŃçªĦ
    0.10
    åįİ丽
    0.10
    aminer
    0.09
    èĻ»
    0.09
    RIPT
    0.09
    å¡ijéĢł
    0.09
    åľ¨åŃ¦æł¡
    0.09
    çªĦ
    0.09
     Narrow
    0.09
    ulpt
    0.09
    Activations Density 0.034%

    No Known Activations