© 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. 51190
    Prev
    Next
    INDEX
    Explanations

    bamboo

    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
    æĮ¯ãĤĬ
    -0.08
    æīij
    -0.08
    åĵĦ
    -0.08
    Markup
    -0.08
    IData
    -0.08
    æ³³
    -0.08
    信访
    -0.08
    ItemClick
    -0.08
     pill
    -0.08
    æķŀå¼Ģ
    -0.08
    POSITIVE LOGITS
    ç¬ĭ
    0.11
    箨
    0.10
     bamboo
    0.10
    ä¸įæĸŃåĪĽæĸ°
    0.10
     Bamboo
    0.09
    ç«¿
    0.09
    ç¬ķ
    0.09
    èįĨ
    0.09
    å·½
    0.09
    ãĤ«ãĥ«
    0.08
    Activations Density 0.055%

    No Known Activations