© 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. 57799
    Prev
    Next
    INDEX
    Explanations

    purpose and desired outcomes

    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
    æķıæĦŁ
    -0.10
    åıĹçĽĬ
    -0.09
     Enlight
    -0.08
    unn
    -0.08
    mani
    -0.08
    holm
    -0.08
     benef
    -0.08
    åѤåĦ¿
    -0.08
    éĩįè¦ģåĨħ容
    -0.08
    è¿Ļåıª
    -0.08
    POSITIVE LOGITS
    é¢Ħå®ļ
    0.13
    é¢ĦæľŁ
    0.12
    使åij½
    0.11
     intended
    0.11
    缮æłĩä»»åĬ¡
    0.11
    åıijæĮ¥äºĨ
    0.10
    æĭ¿æĿ¥
    0.10
    ä»»åĭĻ
    0.10
    éĿĸ
    0.10
     пÑĢедназнаÑĩен
    0.09
    Activations Density 0.060%

    No Known Activations