© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37174
    Prev
    Next
    INDEX
    Explanations

    game development

    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
    ä¿Ĺ
    -0.10
    翼
    -0.08
    gent
    -0.08
    /***/
    -0.08
    andin
    -0.08
    _Config
    -0.08
    åīįéĿ¢
    -0.08
    å±±èĦī
    -0.08
    çİĩåħĪ
    -0.08
    _utf
    -0.08
    POSITIVE LOGITS
     Kickstarter
    0.11
    å°ıå°ı
    0.10
    ä¸İä¼Ĺ
    0.10
    失ä¸ļ
    0.09
    产éĶĢ
    0.09
    åķĨä¼ļ
    0.09
    ä»įåľ¨
    0.09
    åIJİå¤ĩ
    0.09
    ä¼ĹçŃ¹
    0.09
    æķĻåŃ¦è´¨éĩı
    0.09
    Activations Density 0.146%

    No Known Activations