© 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. 18261
    Prev
    Next
    INDEX
    Explanations

    software and product publishing

    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
    å§Ķ
    -0.10
     Sour
    -0.09
    åĽ´è§Ĥ
    -0.09
    oldt
    -0.09
     Mish
    -0.08
     sh
    -0.08
    éĽ¾
    -0.08
    æĶ¹éĿ©å§Ķ
    -0.08
    Commission
    -0.08
    .sem
    -0.08
    POSITIVE LOGITS
    软件
    0.11
    èĽ°
    0.10
    software
    0.10
    è¸ı
    0.09
    ä¹°çļĦ
    0.09
    ç»ıéĶĢ
    0.09
    åıijè¡Į
    0.09
    åįĵ
    0.09
     software
    0.09
    _CD
    0.09
    Activations Density 0.131%

    No Known Activations