© 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. 57702
    Prev
    Next
    INDEX
    Explanations

    importance and significance

    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
    urt
    -0.09
    误导
    -0.09
    åĬłå¤§å¯¹
    -0.09
    çĺĹ
    -0.08
    rze
    -0.08
    èł¢
    -0.08
    neau
    -0.08
    éĹ°
    -0.08
    /flutter
    -0.08
    urdy
    -0.08
    POSITIVE LOGITS
    对ä»ĸ们
    0.19
    ä»ĸ认为
    0.17
     باÙĦÙĨسبة
    0.15
    ä»ĸ们ä¼ļ
    0.14
    ä»ĸ们
    0.14
    ãģ¨æĢĿãģ£ãģ¦ãģĦãĤĭ
    0.13
    åľ¨ä»ĸçļĦ
    0.13
    åľ¨ä»ĸ
    0.13
    ä»ĸ们éĥ½
    0.12
    ä»ĸä¼ļ
    0.11
    Activations Density 0.183%

    No Known Activations