© 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. 38237
    Prev
    Next
    INDEX
    Explanations

    phone calls and discussion

    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
    doch
    -0.09
    ŀæĢ§
    -0.09
    è¶ĭ
    -0.08
    éŃģ
    -0.08
    ç«Ļ
    -0.08
    æīij
    -0.08
     обÑĢаÑĤ
    -0.08
    æ¹Ľ
    -0.08
    _execution
    -0.08
    ãĥĹãĥ¬
    -0.08
    POSITIVE LOGITS
    åIJ¬èµ·æĿ¥
    0.13
    éĢļè¯Ŀ
    0.12
    ä¼łçľŁ
    0.10
    说åĩº
    0.10
     callers
    0.10
    åĸĭ
    0.10
    缴æĴŃéĹ´
    0.10
    æİ¥åIJ¬
    0.10
    æĻ®éĢļè¯Ŀ
    0.09
    å½ķéŁ³
    0.09
    Activations Density 0.075%

    No Known Activations