© 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. 35519
    Prev
    Next
    INDEX
    Explanations

    stock, vanilla, factory, default

    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
    æģ£
    -0.10
    åĬ©åѦ
    -0.10
     онлайн
    -0.09
    å¤ļåħĥåĮĸ
    -0.09
     Prefer
    -0.09
    immers
    -0.09
    æ»Ķ
    -0.08
    åįķ项
    -0.08
    éĻ¬
    -0.08
    æĽ´å¤ļä¿¡æģ¯
    -0.08
    POSITIVE LOGITS
    /original
    0.10
    æĸ°ä¸ī
    0.10
    ijo
    0.10
    çĶ»çĶ»
    0.09
    å®ĺæĸ¹
    0.09
    çļĦä¸ľè¥¿
    0.09
    缴å±ŀ
    0.09
    èĩªå¸¦
    0.09
    è¬Ŀ
    0.08
     vanilla
    0.08
    Activations Density 0.108%

    No Known Activations