© 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. 7034
    Prev
    Next
    INDEX
    Explanations

    politicians' names

    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
    楷
    -0.09
     ç¼
    -0.09
    erture
    -0.08
     Tops
    -0.08
    _enter
    -0.08
    åĽ«
    -0.08
     اÙĦÙħص
    -0.08
    SSIP
    -0.08
    æĻ®åıĬ
    -0.08
    stars
    -0.08
    POSITIVE LOGITS
    æģ¸
    0.09
    enia
    0.09
    æĿ¯
    0.09
    æĮ½
    0.09
    æĬ±
    0.08
    è´±
    0.08
    åİŁå§ĭ
    0.08
    iw
    0.08
    æĶ¶æĭ¾
    0.08
     Wag
    0.08
    Activations Density 0.154%

    No Known Activations