© 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. 17504
    Prev
    Next
    INDEX
    Explanations

    what makes [X] tick

    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
    اÙģت
    -0.09
    å²Ľ
    -0.09
    {{{
    -0.08
    _URI
    -0.08
    çļĦç»ıåİĨ
    -0.08
     yourself
    -0.08
    åı¶
    -0.08
     yourselves
    -0.07
     ÄIJi
    -0.07
     ISO
    -0.07
    POSITIVE LOGITS
    æĪIJè´¥
    0.13
    æĺİæĺİ
    0.10
    ä¸Ĭåįĥ
    0.10
    为ä»Ģä¹Īä¼ļ
    0.10
    éĤ£ä¹Īå¤ļ
    0.09
    羣æŃ£çļĦ
    0.09
    è¿Ļ家åħ¬åı¸
    0.09
    chas
    0.09
    åľ¨è¿Ļ个
    0.09
    让æĤ¨
    0.09
    Activations Density 0.098%

    No Known Activations