© 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. 31337
    Prev
    Next
    INDEX
    Explanations

    followed correctly

    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
    è´¯éĢļ
    -0.09
    ä¸ĭè°ĥ
    -0.09
    管åĪ¶
    -0.09
    é»İæĺİ
    -0.08
    æķŀå¼Ģ
    -0.08
    inki
    -0.08
    æī©æķ£
    -0.08
    èıŁ
    -0.08
    å®ĺ
    -0.08
    è¾Ł
    -0.08
    POSITIVE LOGITS
    ç«łç¨ĭ
    0.13
    åħ¬åı¸ç«łç¨ĭ
    0.12
    è®®äºĭ
    0.12
    åĨ³è®®
    0.10
    çıŃåŃIJ
    0.09
    çĽijäºĭä¼ļ
    0.09
    èĤ¡æĿĥ转让
    0.09
    èij£äºĭä¼ļ
    0.09
    éĢī举
    0.09
    宪
    0.09
    Activations Density 0.029%

    No Known Activations