© 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. 57662
    Prev
    Next
    INDEX
    Explanations

    person who

    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
    ä½Ĩå®ĥ
    -0.11
    èħ¾
    -0.08
     tÃłn
    -0.08
    æ¯Ķå¦Ĥ
    -0.08
    æ·¬
    -0.08
    illy
    -0.08
    é¼İ
    -0.08
    æ¯Ķå¦Ĥ说
    -0.08
    ä½Ĩ她
    -0.08
    è¿Ļäºĭ
    -0.08
    POSITIVE LOGITS
     اÙĦØ°ÙĬ
    0.09
    ç»Ģ
    0.09
    家ä½ı
    0.09
    sworth
    0.09
    åıĬåħ¶
    0.09
    åħ¼ä»»
    0.08
    eto
    0.08
    lop
    0.08
     omnip
    0.08
    ä¸Ģåıªæīĭ
    0.08
    Activations Density 0.053%

    No Known Activations