© 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. 58868
    Prev
    Next
    INDEX
    Explanations

    button inputs: y, select, start, b

    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
    åıijå±ķ空éĹ´
    -0.08
    åĪ©çĶ¨çİĩ
    -0.08
    ç¬ı
    -0.08
    _alive
    -0.08
    owa
    -0.08
    ä¸İä¸ŃåĽ½
    -0.08
    ØŃÙĬاء
    -0.08
    é«ĺéĢŁ
    -0.08
     IR
    -0.08
    xfb
    -0.08
    POSITIVE LOGITS
    注æĺİ
    0.10
    /sources
    0.10
    бил
    0.09
    翻身
    0.09
    éĢ¼
    0.09
     Passing
    0.09
    ru
    0.09
    认è´Ń
    0.09
    ç¢Į
    0.09
    ided
    0.08
    Activations Density 0.031%

    No Known Activations