© 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. 11438
    Prev
    Next
    INDEX
    Explanations

    namespace or class names

    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
    åħļæĢ»
    -0.10
    åģĮ
    -0.09
    æIJ¬å®¶
    -0.09
    衽
    -0.08
    èĩªæĿ¥æ°´
    -0.08
    åı£å¾Ħ
    -0.08
    é»ijçĻ½
    -0.08
    åĬ¨åijĺ
    -0.08
    ç¬ij
    -0.08
    ugu
    -0.08
    POSITIVE LOGITS
    ç»Ħ
    0.10
    纫
    0.09
     Adj
    0.09
    TEX
    0.09
    bulk
    0.09
    été
    0.08
    _eof
    0.08
    骨
    0.08
    ULK
    0.08
    yii
    0.08
    Activations Density 0.208%

    No Known Activations