© 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. 35396
    Prev
    Next
    INDEX
    Explanations

    website links

    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
    æĹ¥æĬ¥ç¤¾
    -0.09
    AWN
    -0.09
     Meadow
    -0.09
    åĪ°æĿ¥
    -0.09
    _disconnect
    -0.08
    ä¸ĬéŨ
    -0.08
    èĶij
    -0.08
    ä¸ŃåŃĺåľ¨çļĦ
    -0.08
    rage
    -0.08
    ä»Ģä¹ĪåİŁåĽł
    -0.08
    POSITIVE LOGITS
    umm
    0.08
     ftp
    0.08
    ftp
    0.08
     FTP
    0.08
     mist
    0.08
    atcher
    0.08
    åıĺæĢģ
    0.07
     Remix
    0.07
    æµĨ
    0.07
    宾客
    0.07
    Activations Density 0.106%

    No Known Activations