© 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. 8939
    Prev
    Next
    INDEX
    Explanations

    University of

    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
    家乡
    -0.10
    ç¥ĸåĽ½
    -0.10
    /use
    -0.10
    çħ
    -0.09
    oundation
    -0.09
    ew
    -0.09
    UMENT
    -0.09
    ç»Ħç»ĩçĶŁæ´»
    -0.09
    ulous
    -0.09
    ould
    -0.09
    POSITIVE LOGITS
    wide
    0.12
    yard
    0.10
    æ³ķ人
    0.10
    -wide
    0.10
    aub
    0.09
    crest
    0.09
    psilon
    0.09
    åĩºçīĪ社
    0.09
    Ø´ÙĬ
    0.09
    yards
    0.09
    Activations Density 0.035%

    No Known Activations