© 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. 36487
    Prev
    Next
    INDEX
    Explanations

    adoption and adopted

    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
    æħİéĩį
    -0.10
    -0.09
    åĨįéĢł
    -0.08
    ãģ¾ãģ£ãģŁãģı
    -0.08
    欧å¼ı
    -0.08
    è®©æĽ´å¤ļ
    -0.08
    åĢ¨
    -0.08
    å¦Ĥæľī
    -0.08
    主人
    -0.08
    oning
    -0.08
    POSITIVE LOGITS
    é½IJé²ģ
    0.09
    ees
    0.09
    _PCM
    0.09
    夫
    0.09
    imit
    0.08
    ÑĤив
    0.08
    辫
    0.08
    ãģĤãģ£ãģ¦
    0.08
    asm
    0.08
    æĿ¼
    0.08
    Activations Density 0.007%

    No Known Activations