© 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. 61620
    Prev
    Next
    INDEX
    Explanations

    distributed under

    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°Ķæĸ¯
    -0.09
    èµĿ
    -0.09
    åĩ»è´¥
    -0.09
    å±ŀäºİèĩªå·±
    -0.09
    QueryString
    -0.09
    åĪĽæĸ°åıijå±ķ
    -0.09
    æİĸ
    -0.09
    æĦļ
    -0.08
    çİĩè¾¾
    -0.08
    iew
    -0.08
    POSITIVE LOGITS
    çľ¼ä¸ĭ
    0.09
    ︱
    0.08
    士
    0.08
    ä½Ĩ对äºİ
    0.08
    atism
    0.08
    椰
    0.08
    主人åħ¬
    0.08
    æ²ī
    0.08
     Reyes
    0.08
    æ°´åĩĨ
    0.08
    Activations Density 0.146%

    No Known Activations