© 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. 31283
    Prev
    Next
    INDEX
    Explanations

    adverbial suffixes like -wise

    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
    å¹²èĦĨ
    -0.10
    itution
    -0.08
    æ²³åįĹ
    -0.08
    ä¹ĭä½ľ
    -0.08
    ogl
    -0.08
    çi
    -0.08
    å·Ŀ
    -0.08
    oba
    -0.08
     Jeg
    -0.08
    _CLR
    -0.08
    POSITIVE LOGITS
    èĢĮè¨Ģ
    0.15
    ä¾Ĩ說
    0.13
    çļĦãģ«ãģ¯
    0.13
    æĿ¥è¯´
    0.13
    æĸ¹éĿ¢
    0.12
    æĿ¥è®²
    0.12
    æĦıä¹īä¸Ĭ
    0.11
     speaking
    0.11
    -wise
    0.11
    æĶ»åĿļ
    0.10
    Activations Density 0.101%

    No Known Activations