© 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. 27143
    Prev
    Next
    INDEX
    Explanations

    recent articles or news

    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
    æ´»
    -0.09
    æľºåĬ¨
    -0.08
    æłĹ
    -0.08
    asil
    -0.08
    è°Īèµ·
    -0.08
    ::_
    -0.08
    ä¹°åįķ
    -0.07
    ãģĹãģ¾ãģĦ
    -0.07
    ç½ij游
    -0.07
    ãģĹãģ¾ãģĨ
    -0.07
    POSITIVE LOGITS
    ä¸Ńåħ±ä¸Ń央
    0.09
    thes
    0.09
    æ¯ħåĬĽ
    0.09
    vais
    0.09
     геÑĢо
    0.09
    ä½İè°ĥ
    0.08
    社ä¼ļåıijå±ķ
    0.08
    WISE
    0.08
    ANO
    0.08
    ëħ¼
    0.08
    Activations Density 0.214%

    No Known Activations