© 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. 50775
    Prev
    Next
    INDEX
    Explanations

    not had, have not, ...n't

    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
    ä¸įåĪ°
    -0.11
    æĺł
    -0.09
    deb
    -0.09
    æ¸į
    -0.09
    åģľçķĻ
    -0.09
    æĢª
    -0.08
    稽
    -0.08
    åĪ©äºļ
    -0.08
    ä¸į代表
    -0.08
    éĩıåĮĸ
    -0.08
    POSITIVE LOGITS
    earer
    0.10
    éĤ£éº¼
    0.09
    ATCH
    0.09
    æľ
    0.09
     ÑģовеÑĢ
    0.09
     cứng
    0.09
    æľīäºĨ
    0.08
    ÑĢÑĥÑĤ
    0.08
    rze
    0.08
    åĿļä¿¡
    0.08
    Activations Density 0.016%

    No Known Activations