© 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. 6597
    Prev
    Next
    INDEX
    Explanations

    awarded by the

    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
    èįĩ
    -0.09
    _UNITS
    -0.09
    æĭĹ
    -0.09
    uther
    -0.08
    ugin
    -0.08
    alers
    -0.08
    æ¯ı个人çļĦ
    -0.08
    _SENS
    -0.08
     evacuated
    -0.08
    dif
    -0.08
    POSITIVE LOGITS
    å½ĵå±Ģ
    0.11
    è¯Ħè®®
    0.10
    éħĴä¸ļ
    0.09
    æĿĥå¨ģ
    0.09
    è¡·
    0.09
    åĽ¢
    0.08
    认åı¯
    0.08
    à¹ģหล
    0.08
    ame
    0.08
    MethodName
    0.08
    Activations Density 0.048%

    No Known Activations