© 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. 9858
    Prev
    Next
    INDEX
    Explanations

    This followed by an assertion

    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
    æĸ¹å¼ıè¿Ľè¡Į
    -0.09
    ather
    -0.09
     undert
    -0.08
    躲
    -0.08
     ÑĤоÑĢ
    -0.08
    ç¨įç¨į
    -0.08
    渡
    -0.08
    dam
    -0.08
     ste
    -0.08
    ucc
    -0.08
    POSITIVE LOGITS
    æĺ¯åľ¨
    0.12
    æĺ¯ä»ĸ
    0.11
    æĺ¯ä¸Ģ个
    0.11
    æĺ¯æĪij们
    0.11
    æĺ¯ä½ł
    0.11
    缴æݥ影åĵį
    0.11
    æĺ¯ä¸Ģ件
    0.10
    æĺ¯ä¸Ģ项
    0.09
    使å¾Ĺ
    0.09
    æĺ¯å¾Ī
    0.09
    Activations Density 0.200%

    No Known Activations