© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 7128
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and verbs

    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
    èļ¤
    -0.11
    çļĦ好å¤Ħ
    -0.10
    ä»»ä½ķæĹ¶åĢĻ
    -0.10
    幸ç¦ıæĦŁ
    -0.10
    yal
    -0.09
    没æľīå¿ħè¦ģ
    -0.09
    Plain
    -0.09
    ä¸į论æĺ¯
    -0.09
    æľªç»ı
    -0.09
    æºIJæºIJä¸įæĸŃ
    -0.09
    POSITIVE LOGITS
    åĭī强
    0.18
    ä¸įäºĨ
    0.13
    ä¸Ģå®ļç¨ĭ度
    0.13
    è¿ĺç®Ĺ
    0.13
    -ish
    0.12
    ä½Ĩåį´
    0.11
    ä½Ĩä»į
    0.11
    äºĽè®¸
    0.11
    æľīä¸Ģå®ļçļĦ
    0.11
    æŁIJç§įç¨ĭ度
    0.11
    Activations Density 0.564%

    No Known Activations