© 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. 61576
    Prev
    Next
    INDEX
    Explanations

    worldwide incidence

    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
    æ¯ĶæĪij
    -0.09
     arsch
    -0.09
    说æĪij
    -0.09
    对æĪijæĿ¥è¯´
    -0.09
    è¦ĨçĽĸéĿ¢
    -0.09
    oul
    -0.09
    æĪĺå½¹
    -0.09
    çľĭå¾ħ
    -0.09
    è§Ĭ
    -0.09
    对æĪij
    -0.09
    POSITIVE LOGITS
    鸳
    0.08
    ä¸Ĭä¸ĭ
    0.08
    Symbol
    0.07
    cription
    0.07
    æĵ¢
    0.07
    说æĺİ书
    0.07
    她们
    0.07
    è°ĥæŁ¥æĺ¾ç¤º
    0.07
     presumably
    0.07
    modifiable
    0.07
    Activations Density 0.290%

    No Known Activations