© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22363
    Prev
    Next
    INDEX
    Explanations

    in website

    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
    èĺ§
    -0.10
    æł·çļĦ
    -0.08
    åĨĮ
    -0.08
    æĬ¡
    -0.08
     Covered
    -0.08
    ç¯Ĩ
    -0.08
    _MIDDLE
    -0.08
    rawing
    -0.08
    _CRC
    -0.08
    COPE
    -0.08
    POSITIVE LOGITS
     вал
    0.11
    çļĦä¸ĢéĿ¢
    0.09
    骸
    0.09
    çĿ¦
    0.09
    zag
    0.09
    æĪĸå¤ļæĪĸå°ij
    0.09
    å®ĿçŁ³
    0.09
    æĭ¬
    0.09
    çľĭä¸Ĭåİ»
    0.09
     ná»iji
    0.08
    Activations Density 0.012%

    No Known Activations