© 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. 59000
    Prev
    Next
    INDEX
    Explanations

    sports team names

    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
    STA
    -0.10
    Misc
    -0.09
    è¿Ļç§įäºĭæĥħ
    -0.09
    è¿Ļéĥ¨åĪĨ
    -0.09
    è¿Ļ件
    -0.09
    è¿Ļ家åħ¬åı¸
    -0.09
    好ä¸į容æĺĵ
    -0.08
    èĩªçĦ¶èĢĮçĦ¶
    -0.08
    itic
    -0.08
    EGA
    -0.08
    POSITIVE LOGITS
    æīĭä¸Ń
    0.11
    ä¸įä¿¡
    0.09
    oho
    0.09
     nâ
    0.09
    æŀľåĽŃ
    0.09
    æĤ¨
    0.09
    çģ¾å®³
    0.09
    æŀľ
    0.09
    ãģªãĤĬ
    0.08
    åıijè¡Į
    0.08
    Activations Density 0.028%

    No Known Activations