© 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. 55839
    Prev
    Next
    INDEX
    Explanations

    one thing

    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
    ä¸ĢåĪĻ
    -0.11
    ä¸ĩä¸Ģ
    -0.10
    ä»°
    -0.09
     ведÑĮ
    -0.09
    éĢĭ
    -0.09
    ä¸Ģ侧
    -0.09
    ä¹ĥ
    -0.09
    ç¹ģå¿Ļ
    -0.09
    è°ĵ
    -0.09
    äºĨä¸Ģ份
    -0.09
    POSITIVE LOGITS
    æĭį
    0.09
    ଡ
    0.08
    pos
    0.08
    è¦ģåģļåĪ°
    0.08
     POS
    0.07
    ä¸įåĪ°ä½į
    0.07
    常常
    0.07
     konk
    0.07
    å¾Ģå¾Ģä¼ļ
    0.07
    ury
    0.07
    Activations Density 0.070%

    No Known Activations