© 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. 38656
    Prev
    Next
    INDEX
    Explanations

    names followed by titles or initials

    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
    èµ
    -0.09
    对ä¼ģä¸ļ
    -0.09
    æĬĬè¿Ļ个
    -0.09
    åĬŀäºĭ
    -0.09
    æĬĬæĮģ
    -0.09
    åĸľ
    -0.08
    æįī
    -0.08
     Trap
    -0.08
    磼
    -0.08
    èĩªèIJ¥
    -0.08
    POSITIVE LOGITS
    åĢĴåľ¨
    0.13
    ä¸į幸
    0.13
    çĶŁåij½
    0.13
    æĹłè¾ľ
    0.12
    çīºçī²
    0.12
    人æŃ»äº¡
    0.12
    çļĦçĶŁåij½
    0.11
    æŃ»äº¡
    0.11
    æĤ²åī§
    0.11
    çĶŁåij½çļĦ
    0.11
    Activations Density 0.157%

    No Known Activations