© 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. 38466
    Prev
    Next
    INDEX
    Explanations

    lists with colons or specific punctuation

    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
    paint
    -0.08
    å¦Ĩ
    -0.08
     interview
    -0.08
    ç°ĩ
    -0.08
    ä»ħ代表
    -0.08
    Decoration
    -0.08
    çĴĨ
    -0.08
    主ä¸ļ
    -0.08
    ARAM
    -0.08
    å¼Ģå¹ķå¼ı
    -0.07
    POSITIVE LOGITS
    æIJŃ
    0.10
    èĪĮ头
    0.10
    天çĦ¶
    0.09
    建çŃijå¸Ī
    0.09
    langs
    0.09
    åı«å£°
    0.09
    åĢĴåľ¨
    0.09
    å²ģ以ä¸Ĭ
    0.09
    åIJ±
    0.08
    callable
    0.08
    Activations Density 0.217%

    No Known Activations