© 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. 19181
    Prev
    Next
    INDEX
    Explanations

    build and, hands-on, 2003, crumble in, were you, Courses A, : How, -Stent-Assisted

    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
    éĶIJ
    -0.09
    æĸĩç«łæĿ¥æºIJ
    -0.09
    .orm
    -0.09
    éĵī
    -0.09
    æijĨèĦ±
    -0.09
    æ²®
    -0.09
    éŀł
    -0.09
    æĭĬ
    -0.08
    _party
    -0.08
    uby
    -0.08
    POSITIVE LOGITS
    æIJŃ建
    0.09
    _plane
    0.09
    æ¡ħ
    0.09
    é¹ħ
    0.09
    车主
    0.09
    çŃij
    0.09
    设计æĸ¹æ¡Ī
    0.08
    使èĢħ
    0.08
    ç´ł
    0.08
    管çIJĨèĢħ
    0.08
    Activations Density 0.045%

    No Known Activations