© 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. 27087
    Prev
    Next
    INDEX
    Explanations

    Unity Progress

    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
    çĦ¶æĺ¯
    -0.10
    åIJĦç§į
    -0.09
    被èªī为
    -0.09
    æįŁ
    -0.09
    ields
    -0.09
    ä»Ģä¹Īäºĭ
    -0.08
    æĬĬè¿ĻäºĽ
    -0.08
    管çIJĨå·¥ä½ľ
    -0.08
    een
    -0.08
     bÄĻdÄħ
    -0.08
    POSITIVE LOGITS
     íĨµíķ´
    0.11
     ìľĦíķľ
    0.11
    undy
    0.10
    (Status
    0.09
    çĤ¹çĩĥ
    0.09
    cob
    0.09
     ìľĦíķ´
    0.09
    æľĢ大éĻIJ度
    0.08
    åī§ä¸Ń
    0.08
    atinum
    0.08
    Activations Density 0.011%

    No Known Activations