© 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. 55236
    Prev
    Next
    INDEX
    Explanations

    dates in June

    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
    çļ¿
    -0.10
    年纪
    -0.09
    rou
    -0.08
    pired
    -0.08
    è¿Ļè¾ĪåŃIJ
    -0.08
    ä»ĬçĶŁ
    -0.08
    è·¡
    -0.08
    LIK
    -0.08
    erval
    -0.08
    åIJĪä¸Ģ
    -0.08
    POSITIVE LOGITS
    zilla
    0.11
    æѤäºĭ
    0.10
    åĩłçĻ¾
    0.09
    nard
    0.09
    è¡·
    0.09
    以ä¾Ĩ
    0.09
    orum
    0.09
    ioni
    0.09
    ĭ
    0.09
     trá»Ŀi
    0.09
    Activations Density 0.221%

    No Known Activations