© 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. 56635
    Prev
    Next
    INDEX
    Explanations

    nation 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
    zano
    -0.09
    odata
    -0.09
    raud
    -0.08
    èĪ¬çļĦ
    -0.08
    iest
    -0.08
     oe
    -0.08
    æīĵå¾Ĺ
    -0.08
    _SAN
    -0.08
    fé
    -0.08
    ìŀĦ
    -0.08
    POSITIVE LOGITS
    зов
    0.10
    å¥ĩ迹
    0.10
     absol
    0.09
    æĦıå¤ĸ
    0.09
    顺
    0.09
     extremes
    0.08
    _rat
    0.08
    夥
    0.08
    å¼ĢæºIJ
    0.08
    æĤĸ
    0.08
    Activations Density 0.086%

    No Known Activations