© 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. 57972
    Prev
    Next
    INDEX
    Explanations

    indicated or warranted

    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
    ikal
    -0.09
    latex
    -0.09
    å¯ĵ
    -0.08
    é¹ħ
    -0.08
    æĸĹ
    -0.08
    ï¸
    -0.08
    è¯ł
    -0.08
    ä¸ĢéĹª
    -0.08
    éļ¶å±ŀäºİ
    -0.08
    overs
    -0.08
    POSITIVE LOGITS
    éĩįåŀĭ
    0.09
    ä¹ĭ举
    0.09
    çIJĨçĶ±
    0.08
    /as
    0.08
    ä¼Ĭæĭī
    0.08
     Territory
    0.08
    æ°ijå¿ĥ
    0.08
    æī¾ä¸ª
    0.08
    å¿ĥèĦıçĹħ
    0.08
    åįģ足
    0.08
    Activations Density 0.035%

    No Known Activations