© 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. 31248
    Prev
    Next
    INDEX
    Explanations

    led or lead

    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
    è¿Ļ个éĹ®é¢ĺ
    -0.09
    zos
    -0.09
    羣çIJĨ
    -0.09
    hel
    -0.09
    ä¸Ģ个éĹ®é¢ĺ
    -0.09
    èĿ¶
    -0.08
    常常
    -0.08
    _flight
    -0.08
    ä¸Ģæľ¬ä¹¦
    -0.08
    ç«
    -0.08
    POSITIVE LOGITS
    _PREF
    0.09
    æ±¹
    0.09
    æĭŁ
    0.08
    å
    0.08
    åħīçݯ
    0.08
    å¨ĵ
    0.08
    åѱ
    0.08
    utar
    0.08
    æłĵ
    0.08
    åģ¥åº·æĪIJéķ¿
    0.08
    Activations Density 0.009%

    No Known Activations