© 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. 31355
    Prev
    Next
    INDEX
    Explanations

    template

    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
    åŃ¥
    -0.09
    еÑģÑĮ
    -0.09
    .ser
    -0.09
    æĽľ
    -0.08
    个å¤ļ
    -0.08
    lay
    -0.08
    å·¥ç¨ĭè´¨éĩı
    -0.08
    纯粹
    -0.08
    ünchen
    -0.08
     FP
    -0.08
    POSITIVE LOGITS
    模æĿ¿
    0.13
    åĮ¡
    0.12
     template
    0.12
    åıĤèĢĥèµĦæĸĻ
    0.12
    æĮĩ令
    0.11
    è¦ģæ±Ĥ
    0.11
    èĮĥ
    0.11
    çļĦè¦ģæ±Ĥ
    0.11
    æ¡Ĩæŀ¶
    0.11
    _template
    0.11
    Activations Density 0.215%

    No Known Activations