© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 1491
    Prev
    Next
    INDEX
    Explanations

    let X do Y

    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
    ä½łèĥ½
    -0.12
    æĪijèĥ½
    -0.11
    éħ¬
    -0.10
    èĥ½è®©
    -0.10
    èĥ½æī¾åΰ
    -0.09
    åĩĨå¤ĩ好
    -0.09
    ä¸ŃéĹ´
    -0.09
    èĥ½åľ¨
    -0.09
    ardin
    -0.09
    raq
    -0.09
    POSITIVE LOGITS
    ç»ıæµİåıijå±ķ
    0.09
     freely
    0.09
    带走
    0.08
    çł´äº§
    0.08
    èĩªå¦Ĥ
    0.08
    娥
    0.08
    鹤
    0.08
    è¿ĽæĿ¥
    0.08
    责任ç¼ĸè¾ij
    0.08
    çļ±
    0.08
    Activations Density 0.068%

    No Known Activations