© 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. 32729
    Prev
    Next
    INDEX
    Explanations

    parenthetical years

    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
    人人éĥ½
    -0.09
    çªģå¦Ĥ
    -0.09
    alysis
    -0.09
    æĪijçĪ±ä½ł
    -0.09
    æİı
    -0.09
    åĵªæĢķæĺ¯
    -0.08
    gaben
    -0.08
    arendra
    -0.08
    åıĤèĢĥèµĦæĸĻ
    -0.08
    å®ī举
    -0.08
    POSITIVE LOGITS
    æµĵ缩
    0.09
    _literals
    0.09
    ç¬ijéģĵ
    0.08
    ç¬ijçĿĢ说
    0.08
    æĻ¨
    0.08
    ITA
    0.08
    agit
    0.08
     aud
    0.08
    éĩįçĤ¹åħ³æ³¨
    0.08
    çľĭä¸įåĩº
    0.08
    Activations Density 0.108%

    No Known Activations