© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31529
    Prev
    Next
    INDEX
    Explanations

    software and programs

    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
    leh
    -0.10
    ç½ij
    -0.10
    éĶļ
    -0.09
    æĬ½çĥŁ
    -0.09
    extracomment
    -0.09
    åIJ¬è¯¾
    -0.09
    vation
    -0.08
    .gt
    -0.08
    ä¸Ģå°ģ
    -0.08
    ä»·åĢ¼éĵ¾
    -0.08
    POSITIVE LOGITS
    软件
    0.12
     software
    0.11
     Herz
    0.09
    software
    0.09
    ç¨ĭåºı
    0.09
    交éĢļå·¥åħ·
    0.09
    ä¼ļéķ¿
    0.09
    篷
    0.09
     scalp
    0.08
    èĵ¬
    0.08
    Activations Density 0.065%

    No Known Activations