© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36228
    Prev
    Next
    INDEX
    Explanations

    docker psCREATED Description

    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
     PACKET
    -0.09
    å·¥ä½ľç»ıéªĮ
    -0.08
     classics
    -0.08
    ä¸ĸ家
    -0.08
     mus
    -0.08
    ä½ľèĢħæīĢæľī
    -0.08
    é«ĺ涨
    -0.08
    çīĪæĿĥ声æĺİ
    -0.08
     nil
    -0.07
    æİĴéĺŁ
    -0.07
    POSITIVE LOGITS
    vey
    0.10
    伸
    0.10
    å¾ħ
    0.09
     полÑĮзÑĥ
    0.09
    kke
    0.09
    Cpp
    0.09
    æ¾İæ¹ĥ
    0.08
    çĦ¶åIJİåĨį
    0.08
    ADVERTISEMENT
    0.08
     toll
    0.08
    Activations Density 0.183%

    No Known Activations