© 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. 18306
    Prev
    Next
    INDEX
    Explanations

    code generated by

    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
    ä»ij
    -0.09
    åŁ·
    -0.09
    å¼ĢæĿ¥
    -0.09
    ved
    -0.08
    æIJ¶
    -0.08
    æľ¬åŁºéĩij
    -0.08
    æ°ijæĹıæĸĩåĮĸ
    -0.08
    çĿ£
    -0.08
    æĦģ
    -0.08
    妤
    -0.08
    POSITIVE LOGITS
    ç»ĦåĽ¾
    0.09
    åıĮæīĭ
    0.09
     piston
    0.08
    gia
    0.08
    inati
    0.08
    æĢ»è§īå¾Ĺ
    0.08
     pap
    0.08
    UInt
    0.08
    éħ¬
    0.08
    fcn
    0.08
    Activations Density 0.025%

    No Known Activations