© 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. 8922
    Prev
    Next
    INDEX
    Explanations

    body cameras

    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
    åĮĹæĸ¹
    -0.09
    çĦī
    -0.09
    ä¿¡æģ¯å®īåħ¨
    -0.09
    æ²ĵ
    -0.08
    è¿Ń
    -0.08
    ä¸Ģ件äºĭ
    -0.08
    ек
    -0.08
    æĮĸæİĺ
    -0.08
    æĢ¥
    -0.08
    (TM
    -0.08
    POSITIVE LOGITS
    æīĭ表
    0.09
    бÑĢ
    0.08
    å¢Ļå£ģ
    0.08
    .bz
    0.08
    _ipc
    0.08
     IDR
    0.08
    严èĤĥ
    0.08
    çĽijæݧ
    0.08
    çģŃ亡
    0.08
     watch
    0.08
    Activations Density 0.116%

    No Known Activations