© 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. 53773
    Prev
    Next
    INDEX
    Explanations

    knowing that

    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¸Ī
    -0.10
    å°±æѤ
    -0.09
    sez
    -0.09
    对ç«ĭ
    -0.08
     liar
    -0.08
    æĭħ
    -0.08
    phen
    -0.08
    å¼Ľ
    -0.08
    åĩºæĿ¥
    -0.08
     Durant
    -0.08
    POSITIVE LOGITS
    çŁ¥éģĵèĩªå·±
    0.16
     knowing
    0.16
    çŁ¥éģĵ
    0.14
     Knowing
    0.12
    éļIJ约
    0.12
    è§īå¾Ĺèĩªå·±
    0.11
    ysis
    0.10
    unge
    0.10
    åķĸ
    0.10
    æ·±çŁ¥
    0.10
    Activations Density 0.039%

    No Known Activations