© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7920
    Prev
    Next
    INDEX
    Explanations

    names ending in -son or -sen

    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
    è¿ĻäºĽéĥ½æĺ¯
    -0.11
    æķij人
    -0.09
    ity
    -0.09
     scape
    -0.09
    æ£ĭ
    -0.09
    溽
    -0.09
    ä»Ģ麽
    -0.08
    {{{
    -0.08
    ç¾¹
    -0.08
    å¾ľ
    -0.08
    POSITIVE LOGITS
    gist
    0.10
    å¨ĺ
    0.10
    gere
    0.10
    angi
    0.10
    goo
    0.09
     Sty
    0.09
    ddy
    0.09
    ipp
    0.09
    梢
    0.09
    itecture
    0.08
    Activations Density 0.003%

    No Known Activations