© 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. 17756
    Prev
    Next
    INDEX
    Explanations

    look at/like/good

    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
    pto
    -0.08
    ä¸Ģåľº
    -0.08
    bat
    -0.08
    缸å¤Ħ
    -0.08
    èİ«è¿ĩäºİ
    -0.08
    ilen
    -0.08
    åĪ©
    -0.08
     topp
    -0.08
    tam
    -0.07
    éĹº
    -0.07
    POSITIVE LOGITS
    åĽŀæĥ³
    0.09
    åĽŀ头çľĭ
    0.09
    å¨ģ
    0.09
    æĺ¾å¾Ĺ
    0.09
    ç»Łè®¡æķ°æį®
    0.08
    ç¹ģå¿Ļ
    0.08
    åĽŀé¦ĸ
    0.08
    аниз
    0.08
    æĨİ
    0.08
    ivr
    0.08
    Activations Density 0.032%

    No Known Activations