© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22119
    Prev
    Next
    INDEX
    Explanations

    visualizer waveform image

    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
    æ¸ĹéĢı
    -0.12
    onic
    -0.10
    墨
    -0.09
    éģĹæ¼ı
    -0.09
    æŃ£æĸĩ
    -0.09
    IPHER
    -0.09
     Shr
    -0.09
    åIJĮç±»
    -0.09
    浸
    -0.09
    /banner
    -0.09
    POSITIVE LOGITS
    å®ŀæŶ
    0.10
    æī¬
    0.09
    çŀ¬
    0.09
    /live
    0.09
    TH
    0.08
    èµ·ä¼ı
    0.08
     quint
    0.08
    åijĪ
    0.08
    Pow
    0.08
    解说
    0.08
    Activations Density 0.071%

    No Known Activations