© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36163
    Prev
    Next
    INDEX
    Explanations

    higher, greater, larger, faster

    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
    åħ¥ä½ı
    -0.09
    èĦ¸èī²
    -0.09
    _ctl
    -0.09
    ãģªãģĭ
    -0.09
    ä¸įéĻIJ
    -0.08
    æĪį
    -0.08
    avage
    -0.08
    çļĦæĥ³æ³ķ
    -0.08
    çŃĸåĪĴ
    -0.08
    .sav
    -0.08
    POSITIVE LOGITS
    æĽ´é«ĺçļĦ
    0.15
    æĽ´é«ĺ
    0.13
    æĽ´å¤§çļĦ
    0.13
    é«ĺå³°
    0.12
    æĸ°çļĦ
    0.11
    æĽ´å¿«
    0.11
    æĶĢçĻ»
    0.10
    æĽ´æ·±
    0.10
    åīįè¿Ľ
    0.10
    æĶĢåįĩ
    0.10
    Activations Density 0.076%

    No Known Activations