© 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. 51813
    Prev
    Next
    INDEX
    Explanations

    enumerated lists

    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
    è©
    -0.09
    ä¼ĹæīĢ
    -0.08
    说çĿĢ
    -0.08
    ä¸įèµ·
    -0.08
    OMET
    -0.08
    è¿Ļéĥ¨åĪĨ
    -0.08
    loe
    -0.08
     Hamp
    -0.07
    onde
    -0.07
    nap
    -0.07
    POSITIVE LOGITS
     Flyers
    0.10
    èĢIJå¿ĥ
    0.10
    _Framework
    0.09
    rollo
    0.09
    çĥŃæĥħ
    0.09
    快讯
    0.09
    åıªè§ģ
    0.09
    æī§åĭ¤
    0.09
    æĥħ人
    0.09
    ä¸Ģå®ļçļĦ
    0.09
    Activations Density 0.315%

    No Known Activations