© 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. 19071
    Prev
    Next
    INDEX
    Explanations

    applied topically/systemically

    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
    åĬ«
    -0.10
    ç³Ļ
    -0.09
    _GAIN
    -0.09
    è¿ĻæĿ¡è·¯
    -0.09
    еÑģÑĤи
    -0.08
    糯
    -0.08
    hor
    -0.08
    æ±²
    -0.08
    ä¸įåıĺ
    -0.08
    ä¿ĺ
    -0.08
    POSITIVE LOGITS
    çĶ¨éĩı
    0.12
     applic
    0.10
    æĸ½
    0.10
    ç»ĵ
    0.09
    åºĶçĶ¨äºİ
    0.09
    æľīæķĪæľŁ
    0.09
     EOF
    0.09
    éĢıæĺİ
    0.08
     applies
    0.08
    _maps
    0.08
    Activations Density 0.048%

    No Known Activations