© 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. 56493
    Prev
    Next
    INDEX
    Explanations

    right expressions

    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
    麼
    -0.11
    wap
    -0.09
    åıĺéĢŁ
    -0.09
    饺
    -0.09
    çİ«
    -0.09
    ä¸ĭåįĬ
    -0.09
    大æĸ¹
    -0.08
    åī©ä¸ĭ
    -0.08
    å®ĺæĸ¹å¾®ä¿¡
    -0.08
    åķĨä¸ļåĮĸ
    -0.08
    POSITIVE LOGITS
    鹦
    0.11
    é¢ĦçķĻ
    0.09
    æºľ
    0.09
    CSV
    0.08
    éĻªä½ł
    0.08
    gra
    0.08
    åı¯æĥ³
    0.08
     hữu
    0.08
     ÑĢаÑģпол
    0.08
    ä¹Łå¥½
    0.08
    Activations Density 0.026%

    No Known Activations