© 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. 17876
    Prev
    Next
    INDEX
    Explanations

    currently followed by state

    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
    å¤ļå¹´æĿ¥
    -0.10
    å±ĭéĩĮ
    -0.10
    è¦ģæľī
    -0.10
    å½ĵåĪĿ
    -0.10
    缮åīįå·²
    -0.09
    趴
    -0.09
    éĻĢ
    -0.09
    è´Ń
    -0.09
    æĪijå½ĵæŶ
    -0.09
    salt
    -0.09
    POSITIVE LOGITS
    izr
    0.10
    æľīä¸Ģç§į
    0.09
    主导
    0.09
    tit
    0.08
    aries
    0.08
    åı¦ä¸Ģ
    0.08
    ä»»ä½ķå½¢å¼ı
    0.08
    æĦıä¹īä¸ĬçļĦ
    0.08
    جر
    0.08
     Ruiz
    0.08
    Activations Density 0.057%

    No Known Activations