© 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. 5760
    Prev
    Next
    INDEX
    Explanations

    executive director, CEO, director

    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
    éĻ¢åī¯éĻ¢éķ¿
    -0.12
    eries
    -0.10
    ä¹İ
    -0.10
    è´£ç¼ĸ
    -0.10
    äºĭä¸ļéĥ¨
    -0.10
    ä¿ĿéĻ©åħ¬åı¸
    -0.09
    æĴij
    -0.09
    rotch
    -0.09
    çĸ£
    -0.09
    æĸ¯é¡¿
    -0.09
    POSITIVE LOGITS
    æ±
    0.08
    iasco
    0.08
    2
    0.08
    ç´¯
    0.07
    å¯Ĵåģĩ
    0.07
    iona
    0.07
    7
    0.07
     deb
    0.07
    Race
    0.07
    åijĺ
    0.07
    Activations Density 0.012%

    No Known Activations