© 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. 2656
    Prev
    Next
    INDEX
    Explanations

    charter member or first director

    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
    主åĬ¨
    -0.10
    å±Ĥå±Ĥ
    -0.10
    çĪ·
    -0.09
    ç²¹
    -0.09
    ç¿
    -0.09
    åĭĩæķ¢
    -0.08
    è¾ħ
    -0.08
    çģµæķı
    -0.08
    åĩ½
    -0.08
     ÙĨÙĬ
    -0.08
    POSITIVE LOGITS
     inaugural
    0.15
    é¦ĸå±Ĭ
    0.14
    æĪIJç«ĭ以æĿ¥
    0.14
    第ä¸Ģå±Ĭ
    0.14
    é¦ĸæī¹
    0.14
    第ä¸Ģæī¹
    0.14
    ä¹ĭåĪĿ
    0.13
    åĪĿæľŁ
    0.13
    第ä¸Ģ个
    0.12
    çŃ¹å»º
    0.12
    Activations Density 0.196%

    No Known Activations