© 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. 3339
    Prev
    Next
    INDEX
    Explanations

    Cape Cod locations

    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
    ä¸Ģçīĩ
    -0.09
     rog
    -0.09
    家ä½ı
    -0.08
    loff
    -0.08
     LENG
    -0.08
    绾
    -0.08
    hdr
    -0.08
    åĴı
    -0.08
    èľĢ
    -0.08
    åİ»åĮ»éĻ¢
    -0.08
    POSITIVE LOGITS
    ç´ł
    0.11
    æĿijéķĩ
    0.10
    æ³¥åľŁ
    0.10
    esian
    0.09
    æŀ¶åŃIJ
    0.09
    çĿĢ
    0.09
     Weston
    0.09
    ghan
    0.09
    çŃīåľ°
    0.09
    emen
    0.09
    Activations Density 0.004%

    No Known Activations