© 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. 58143
    Prev
    Next
    INDEX
    Explanations

    built by Connor, 18th century, mid-14th century

    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
    çĶ°éĩİ
    -0.09
    æİ¥è¿ĩ
    -0.09
    èĨĪ
    -0.09
    æIJŃæ¡£
    -0.09
    çªľ
    -0.09
    çľ¼ä¸ĭ
    -0.08
    æ³±
    -0.08
    蹿
    -0.08
    ç»ļ丽
    -0.08
    涯
    -0.08
    POSITIVE LOGITS
    建æĪIJåIJİ
    0.10
    建éĢł
    0.10
    å§ĭ建
    0.09
    è§ĦåĪĴ建设
    0.09
    修建
    0.09
    åĪĨæľŁ
    0.09
    åĿĢ
    0.08
    สร
    0.08
    æĨ©
    0.08
    建
    0.08
    Activations Density 0.492%

    No Known Activations