© 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. 61025
    Prev
    Next
    INDEX
    Explanations

    estimates and approximations

    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
    æĺİæĺİ
    -0.11
    çĭ
    -0.10
     Cald
    -0.09
    æļĹ
    -0.09
    èij³
    -0.09
    æIJ¦
    -0.09
    亮
    -0.09
    èݳ
    -0.09
    aland
    -0.08
    ä¸¥æł¼æĮīçħ§
    -0.08
    POSITIVE LOGITS
    大èĩ´
    0.17
     rough
    0.13
     general
    0.12
    ç²Ĺ
    0.12
    大æ¦Ĥ
    0.11
    缸è¿ij
    0.10
    rough
    0.10
    åıªæĺ¯ä¸Ģ个
    0.10
    èĪ¬
    0.10
    eneral
    0.09
    Activations Density 0.062%

    No Known Activations