© 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. 23390
    Prev
    Next
    INDEX
    Explanations

    working by dedicated people

    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
    æľīçĽĬ
    -0.09
    ATO
    -0.08
    ç»ķ
    -0.08
    .ft
    -0.08
    æĪij们éľĢè¦ģ
    -0.08
    ฯ
    -0.08
    åĪĨä¼ļ
    -0.08
    _TA
    -0.08
     franca
    -0.08
    èĴ¿
    -0.08
    POSITIVE LOGITS
    åħ±åIJĮåĬªåĬĽ
    0.14
    åĬŁåĬ³
    0.13
    åĬªåĬĽ
    0.12
    çļĦåĬªåĬĽ
    0.11
    è¾Ľåĭ¤
    0.11
    æīįèĥ½
    0.11
    åħ¨ä½ĵåijĺå·¥
    0.11
     ÑĥÑģили
    0.10
    é»ĺå¥ij
    0.10
    æİ¥åĬĽ
    0.10
    Activations Density 0.182%

    No Known Activations