© 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. 32940
    Prev
    Next
    INDEX
    Explanations

    thank you / mentality / sending

    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
    akan
    -0.09
    å¼ķ
    -0.09
    åĩij
    -0.09
    头çļ®
    -0.08
    _TODO
    -0.08
    åŀĤ
    -0.08
    祺
    -0.08
     TáºŃp
    -0.08
     Wise
    -0.08
    æĭ¬
    -0.08
    POSITIVE LOGITS
    æĦŁè¬Ŀ
    0.13
    åĽŀé¦Ī
    0.12
    æĦŁè°¢
    0.12
    æĦŁæ¿Ģ
    0.11
    æĦŁæģ©
    0.11
    ç´ł
    0.11
     благодаÑĢ
    0.11
    谢谢
    0.10
     thanking
    0.10
     thank
    0.10
    Activations Density 0.073%

    No Known Activations