© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21012
    Prev
    Next
    INDEX
    Explanations

    Anglican bishop

    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
    mur
    -0.10
    åİ¿éķ¿
    -0.09
    airo
    -0.08
     Lowe
    -0.08
    é¢ı
    -0.08
    为èĩªå·±
    -0.08
     gab
    -0.08
    _extractor
    -0.08
    å±±åºĦ
    -0.08
     mur
    -0.08
    POSITIVE LOGITS
    丼æŀĹ
    0.10
    æīĵæĬĺ
    0.10
    æĿĥå¨ģ
    0.10
    æİĸ
    0.09
    lection
    0.09
    åºĦ严
    0.09
    é¢Ĩè¢ĸ
    0.09
    OUCH
    0.09
    æķĻåłĤ
    0.08
    åijĹ
    0.08
    Activations Density 0.194%

    No Known Activations