© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8841
    Prev
    Next
    INDEX
    Explanations

    brown rice or quinoa

    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
    弥补
    -0.09
    绽
    -0.08
    ç¼Ģ
    -0.08
    èIJ½åĪ°
    -0.08
    Ñĥл
    -0.07
    adol
    -0.07
    .Prot
    -0.07
    ImageRelation
    -0.07
    åij½è¿IJ
    -0.07
    è¿ĺè¦ģ
    -0.07
    POSITIVE LOGITS
    åĩĨå¤ĩ
    0.09
    æ·±åĮĸæĶ¹éĿ©
    0.09
    ä¸Ģå¥Ĺ
    0.09
    çķĮ
    0.09
    åķ·
    0.09
    趸
    0.09
    bots
    0.08
    _grp
    0.08
    ä¸Ģ大
    0.08
     ingredients
    0.08
    Activations Density 0.045%

    No Known Activations