© 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. 32969
    Prev
    Next
    INDEX
    Explanations

    vegetables and produce

    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
    ä½ľé£İ建设
    -0.10
    伪
    -0.10
    éĺĹ
    -0.09
    å°±ä¸ļå²Ĺä½į
    -0.09
    ç»ĪçĶŁ
    -0.09
    大åıij
    -0.09
    æľįåĬ¡åijĺ
    -0.09
     воп
    -0.09
    身æĿIJ
    -0.09
    èĩ³å°Ĭ
    -0.09
    POSITIVE LOGITS
    åı£å²¸
    0.10
    æĤł
    0.08
    åı¹
    0.08
    çī¯
    0.08
    éħ¸
    0.08
    Ñģло
    0.08
    æµĴ
    0.08
    ish
    0.08
    æµ·éĩı
    0.08
    欢
    0.08
    Activations Density 0.035%

    No Known Activations