© 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. 21231
    Prev
    Next
    INDEX
    Explanations

    major studios and franchises

    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
    åľĪ
    -0.10
    å¾ĺå¾Ĭ
    -0.08
    å½¢
    -0.08
    æ±Ĺæ°´
    -0.08
    æĸ¤
    -0.08
    boat
    -0.08
    åIJĽ
    -0.08
    ä¸Ģåı°
    -0.08
    needle
    -0.08
    abouts
    -0.08
    POSITIVE LOGITS
    å¯Ĵåģĩ
    0.09
    éĢļãĤĬ
    0.09
    olor
    0.09
    å·¡
    0.09
    olas
    0.08
    ì°°
    0.08
    éľŃ
    0.08
    uffed
    0.08
    avig
    0.08
    clr
    0.08
    Activations Density 0.058%

    No Known Activations