© 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. 27569
    Prev
    Next
    INDEX
    Explanations

    Grid, East Erdos, grazing, Tribal Areas

    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
    ä¸Ģæµģ
    -0.09
    æĤŃ
    -0.09
    CLS
    -0.09
    æµĶ
    -0.09
    åĴĮå°ļ
    -0.09
    .dm
    -0.08
    å¾Ĺ罪
    -0.08
     Dual
    -0.08
    åıĮè¾¹
    -0.08
    æī§æ³ķ人åijĺ
    -0.08
    POSITIVE LOGITS
    éħ¥
    0.11
    åĻ¶
    0.10
     gamm
    0.10
    åŃļ
    0.09
     FA
    0.09
    æĹıèĩªæ²»å·ŀ
    0.09
    icz
    0.09
     Sommer
    0.08
    kaar
    0.08
    翻身
    0.08
    Activations Density 0.139%

    No Known Activations