© 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. 31388
    Prev
    Next
    INDEX
    Explanations

    mic followed by rowave, rop, rom, or ron

    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
    ists
    -0.10
    uil
    -0.09
    OrUpdate
    -0.09
    è¯Ŀ
    -0.09
     Unsafe
    -0.09
    iser
    -0.09
    aud
    -0.09
    atten
    -0.08
    ein
    -0.08
    chaft
    -0.08
    POSITIVE LOGITS
    们
    0.10
    çĦ¶æĺ¯
    0.10
    -sized
    0.10
    æł·çļĦ
    0.09
    lient
    0.09
    Çİ
    0.09
    ÑĢоÑģ
    0.09
    ography
    0.09
    ãģĵãģ¨ãģ¯
    0.09
    æĺī
    0.09
    Activations Density 0.013%

    No Known Activations