© 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. 54424
    Prev
    Next
    INDEX
    Explanations

    driving and cars

    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
    踢
    -0.09
    èĥ´
    -0.09
    æĬĢèĥ½åŁ¹è®Ń
    -0.09
    nock
    -0.08
    ä¸ļä½Ļ
    -0.08
    楼梯
    -0.08
    æīĴ
    -0.08
    æĿłæĿĨ
    -0.08
     FALL
    -0.08
    ç©¿ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    驾车
    0.21
    汽车
    0.20
    车ä¸Ĭ
    0.18
    æĸ¹åIJijçĽĺ
    0.18
    驾驶
    0.18
    è¡Į车
    0.18
    车主
    0.18
    è¡Į驶
    0.18
    车è¾Ĩ
    0.17
    å¼Ģ车
    0.17
    Activations Density 0.105%

    No Known Activations