© 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. 38924
    Prev
    Next
    INDEX
    Explanations

    reporting speech or advice

    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
    دÙī
    -0.10
    宣è¨Ģ
    -0.09
    为èĩªå·±
    -0.09
    ÑĦе
    -0.09
    ä¸Ģé¦ĸ
    -0.09
    å®īåħ¨ä¿Ŀéļľ
    -0.08
    ä¸įçŁ¥ä¸įè§ī
    -0.08
    åIJ¦
    -0.08
    è§īå¾Ĺèĩªå·±
    -0.08
     ÑıвлÑı
    -0.08
    POSITIVE LOGITS
    åĬĿ
    0.14
    ä¸įè¦ģ
    0.14
    é¼ĵåĬ±
    0.13
    åı®åĺ±
    0.13
     advice
    0.11
     advises
    0.11
    åİ»åģļ
    0.11
    ä¸įè¦ģ太
    0.10
     advised
    0.10
    建议
    0.10
    Activations Density 0.089%

    No Known Activations