© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35338
    Prev
    Next
    INDEX
    Explanations

    false or misleading statements

    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
    èµ°åIJij
    -0.09
    误导
    -0.09
    ç»ıæµİåѦ
    -0.09
    dden
    -0.08
    _SDK
    -0.08
    æłijæŀĿ
    -0.08
     PURE
    -0.08
    KNOWN
    -0.08
     junction
    -0.08
    ä¸įåħ¬å¹³
    -0.08
    POSITIVE LOGITS
    amel
    0.10
     Dun
    0.10
    骧
    0.09
    çĻĸ
    0.09
    åħ¨æĹ¥
    0.09
    åijĨ
    0.09
    åķ»
    0.09
    æīĭå·¥
    0.09
    mars
    0.08
    ying
    0.08
    Activations Density 0.012%

    No Known Activations