© 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. 51812
    Prev
    Next
    INDEX
    Explanations

    entertainment studios and companies

    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
    9
    -0.09
    0
    -0.09
    æĮĩ导
    -0.08
    æĻ¯å¾·
    -0.08
    8
    -0.08
    亲身
    -0.08
    天涯
    -0.08
    åĽ¢åijĺ
    -0.08
    4
    -0.08
    5
    -0.08
    POSITIVE LOGITS
    å½±ä¸ļ
    0.09
    è¾ĵåĩº
    0.09
    омеÑĢ
    0.09
    æľīéĻIJåħ¬åı¸
    0.09
    rette
    0.09
    ฯ
    0.09
    æĹĹä¸ĭçļĦ
    0.09
    afx
    0.09
    举åįĹäºļ
    0.09
    çŃīéĥ¨éŨ
    0.09
    Activations Density 0.032%

    No Known Activations