© 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. 28090
    Prev
    Next
    INDEX
    Explanations

    then followed by a verb

    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
    çİ°åľ¨å·²ç»ı
    -0.11
     alike
    -0.11
    æĹ©æĻļ
    -0.10
    è¿Ļä¹Ī说
    -0.10
    ainen
    -0.10
    GMEM
    -0.09
    è¾ĥ强çļĦ
    -0.09
    éļıæŶ
    -0.09
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.09
    _AES
    -0.09
    POSITIVE LOGITS
    m
    0.09
    ats
    0.09
     Smy
    0.08
    ovel
    0.08
    èµ·åĪ°
    0.08
    åıĺæĪIJ
    0.08
    imize
    0.08
    M
    0.08
    享åıĹåĪ°
    0.08
    æĬĬè¿Ļ个
    0.07
    Activations Density 0.019%

    No Known Activations