© 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. 38907
    Prev
    Next
    INDEX
    Explanations

    bantamweight

    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
    0
    -0.09
    paren
    -0.09
    å°ıå°ıçļĦ
    -0.08
    åħ¬ç¤¾
    -0.08
    è¿İæİ¥
    -0.08
    ãĤ»ãĥ³ãĤ¿ãĥ¼
    -0.08
    orate
    -0.08
     ÑĨелÑĮ
    -0.08
    cn
    -0.08
    7
    -0.08
    POSITIVE LOGITS
    åŀĭä¼ģä¸ļ
    0.10
    [sub
    0.10
    ä»»
    0.10
    è¼ķ
    0.10
    è½»
    0.10
    SCALE
    0.10
    æķ¦
    0.09
    å¿«æĬ¥
    0.09
    ä¸ĢçŃīå¥ĸ
    0.09
    æĭ¨æīĵ
    0.09
    Activations Density 0.006%

    No Known Activations