© 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. 53677
    Prev
    Next
    INDEX
    Explanations

    recently described

    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
    ECT
    -0.09
    дÑĥм
    -0.09
     Kang
    -0.09
    ish
    -0.09
    èŁ¾
    -0.08
    æ¯ķä¸ļåIJİ
    -0.08
     paddle
    -0.08
    ille
    -0.08
    涩
    -0.08
    åľ°æĸ¹
    -0.08
    POSITIVE LOGITS
    ä¹¾åĿ¤
    0.09
    æİ©
    0.09
    çł´
    0.09
    ä¸ļ
    0.09
    åij½
    0.08
    NST
    0.08
    使人
    0.08
    主ä¸ļ
    0.08
    ç¾ģ
    0.08
    è°ĥæŁ¥
    0.08
    Activations Density 0.186%

    No Known Activations