© 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. 19069
    Prev
    Next
    INDEX
    Explanations

    difficulty or simplicity

    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
    æIJ¬å®¶
    -0.10
    idget
    -0.09
    沫
    -0.09
    è¿IJè´¹
    -0.09
    FAULT
    -0.09
    ä»İæĿ¥ä¸į
    -0.09
     Fool
    -0.09
     Ñĥдоб
    -0.08
    ä¸į平衡
    -0.08
    _third
    -0.08
    POSITIVE LOGITS
    åİŁåĪĻä¸Ĭ
    0.09
    ä¹Łä¸įæĺ¯
    0.09
    å¾Īå¿«å°±
    0.08
    ä¹Łå¾Ī
    0.08
     enough
    0.08
     surprisingly
    0.08
    æįİ
    0.08
    à¸ķà¸Ļ
    0.08
    åŁĤ
    0.08
    ande
    0.08
    Activations Density 0.203%

    No Known Activations