© 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. 35641
    Prev
    Next
    INDEX
    Explanations

    political leaders' 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
    	TokenName
    -0.09
    arus
    -0.09
     Leban
    -0.09
    é¥
    -0.09
    å¹³åĩ¡
    -0.09
    anches
    -0.09
    缺åı£
    -0.09
    .isOpen
    -0.09
    æĥij
    -0.09
    bish
    -0.09
    POSITIVE LOGITS
    ali
    0.08
    æĦıä¹īä¸ĬçļĦ
    0.08
    ons
    0.08
    æĦıä¹īä¸Ĭ
    0.08
    ä¸Ģä¼ļ
    0.08
    cing
    0.08
    ahoma
    0.07
    ä»İæł¹æľ¬ä¸Ĭ
    0.07
    FW
    0.07
    _FRE
    0.07
    Activations Density 0.147%

    No Known Activations