© 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. 26580
    Prev
    Next
    INDEX
    Explanations

    introduction: factors determine

    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
    umper
    -0.10
    è°¯
    -0.09
    ç»Ļèĩªå·±
    -0.08
     interf
    -0.08
    æĭĵå±ķ
    -0.08
    ocity
    -0.08
    å¼Ģæĭĵ
    -0.08
    èĬĤ
    -0.08
    éĽĨåIJĪ
    -0.08
    丧失
    -0.08
    POSITIVE LOGITS
    æĥ©ç½ļ
    0.13
    веÑģ
    0.10
    ç®Ĺæ³ķ
    0.10
    æĿĥéĩį
    0.10
    è¶ĬæĿ¥è¶Ĭ
    0.10
     Теп
    0.10
    æĪIJ份
    0.09
    åĿį
    0.09
    æīĢè°ĵçļĦ
    0.09
    ibo
    0.09
    Activations Density 0.046%

    No Known Activations