© 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. 30296
    Prev
    Next
    INDEX
    Explanations

    numbers followed by chinese characters

    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
     junction
    -0.09
    oise
    -0.08
    elage
    -0.08
    phans
    -0.08
    ombo
    -0.08
    æ¸
    -0.08
    åĿŀ
    -0.08
    æī¾åĩĨ
    -0.08
    SAVE
    -0.08
    è´§
    -0.08
    POSITIVE LOGITS
    ä¼ģä¸ļåĴĮ
    0.09
    宫殿
    0.09
    æĢ§åĴĮ
    0.09
    fully
    0.09
    婵
    0.09
    å°ıåŃIJ
    0.09
    åħĭåĪ¶
    0.09
    ä¼ĺèī¯
    0.08
     гÑĢÑĥппÑĭ
    0.08
    åħ·ä½ĵæĥħåĨµ
    0.08
    Activations Density 0.305%

    No Known Activations