© 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. 10335
    Prev
    Next
    INDEX
    Explanations

    sitting and watching

    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
    å¤ĸåĽ´
    -0.11
    缶
    -0.09
    åŃº
    -0.09
    åģļ个
    -0.09
     eventual
    -0.09
    è¦ģåģļ
    -0.08
    ä¾ĿéĿł
    -0.08
    ãģ«ãģı
    -0.08
    æĦıè§ģ
    -0.08
    积
    -0.08
    POSITIVE LOGITS
    çľĭçĿĢ
    0.17
    åĽŀæĥ³
    0.14
    çľĭèijĹ
    0.13
    åIJ¬çĿĢ
    0.12
    æľĽçĿĢ
    0.12
    çľĭåĪ°
    0.11
    åĿIJåľ¨
    0.10
    æĥ³èµ·æĿ¥
    0.10
    çľĭäºĨçľĭ
    0.10
    åĽŀåij³
    0.10
    Activations Density 0.095%

    No Known Activations