© 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. 56469
    Prev
    Next
    INDEX
    Explanations

    movement and artifacts

    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
    å¥ļ
    -0.11
    èĩªæľī
    -0.10
    åѤ
    -0.10
    ODE
    -0.10
    éĥģ
    -0.10
    è¤Ĵ
    -0.10
     Lesb
    -0.09
    è¿Ł
    -0.09
     Haj
    -0.08
    åıįæŃ£
    -0.08
    POSITIVE LOGITS
    ä¸įåĬ¨
    0.13
    æIJ½
    0.10
    /bus
    0.10
     movements
    0.09
    姿åĬ¿
    0.09
    åĬ¨éĿĻ
    0.09
    è¿IJåĬ¨ä¼ļ
    0.09
    çļĦåĬ¨ä½ľ
    0.09
    åĬ¨æĦŁ
    0.09
    ä¸Ńæĸ°
    0.08
    Activations Density 0.117%

    No Known Activations