© 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. 5413
    Prev
    Next
    INDEX
    Explanations

    release dates and availability

    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
    ç«ĭ项
    -0.11
    åĩłåįģå¹´
    -0.11
    æĪĸå¤ļ
    -0.10
    æ¯ıä¸Ģ次
    -0.10
    æ¯ı次éĥ½
    -0.09
    åIJįæ°Ķ
    -0.09
    åįģåĩłå¹´
    -0.09
    SimpleName
    -0.09
    ä¸İæŶ
    -0.09
    沧æ¡ij
    -0.09
    POSITIVE LOGITS
    é¦ĸæī¹
    0.13
    çİĩåħĪ
    0.12
    æĬ¢
    0.11
    supply
    0.10
    è¿Ļ两天
    0.10
     Distrib
    0.10
    åĪĿæľŁ
    0.09
    æĬ¢åħĪ
    0.09
     supply
    0.09
    è¿ŀå¤ľ
    0.09
    Activations Density 0.087%

    No Known Activations