© 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. 5442
    Prev
    Next
    INDEX
    Explanations

    reservoir, laboratory, buffer, references, forum

    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
    åĽ½å®¶éĩįçĤ¹
    -0.09
    enties
    -0.09
    âľ³
    -0.09
    åķĨä¸ļåĮĸ
    -0.08
    æĬĬå®ĥ
    -0.08
    ç®Ģæĺĵ
    -0.08
     Lehr
    -0.08
    é¢Ħå¤ĩ
    -0.08
    incer
    -0.08
    ignon
    -0.08
    POSITIVE LOGITS
    æīĭ段
    0.09
    仲
    0.09
     for
    0.09
    æŸ
    0.08
    æĪijä¸įæĺ¯
    0.08
    æ©Ħæ¦Ħ
    0.08
    çļĦä¸Ģéĥ¨åĪĨ
    0.08
    åħįéĻ¤
    0.08
    åħ¼
    0.08
    /source
    0.08
    Activations Density 0.381%

    No Known Activations