© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21331
    Prev
    Next
    INDEX
    Explanations

    instead of conventional

    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
    çĵľ
    -0.10
    çªŁ
    -0.10
    _DSP
    -0.09
    кÑģ
    -0.09
    åĮª
    -0.09
    ìĹ½
    -0.09
    è¡®
    -0.08
    ahren
    -0.08
    示æĦı
    -0.08
    ÑĤин
    -0.08
    POSITIVE LOGITS
    ä¼łç»ŁçļĦ
    0.14
    常è§Ħ
    0.13
     conventional
    0.11
     traditional
    0.11
    åįķ纯çļĦ
    0.10
     usual
    0.10
    æŃ£å¸¸çļĦ
    0.10
    é¦ĸéĢī
    0.10
    寻常
    0.10
    ä¼łç»Ł
    0.09
    Activations Density 0.094%

    No Known Activations