© 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. 36339
    Prev
    Next
    INDEX
    Explanations

    domain names and corporations

    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
    ç¼ī
    -0.08
    ç§ijæķĻ
    -0.08
    0
    -0.08
    itag
    -0.08
    å¨ģåĬĽ
    -0.07
    2
    -0.07
    1
    -0.07
    ãĥĢãĥ³
    -0.07
    ç¾Ĭ
    -0.07
     Liber
    -0.07
    POSITIVE LOGITS
    åķĨæłĩ
    0.13
    注åĨĮ
    0.12
    æ£ī
    0.11
     trademark
    0.10
    çĿģå¼Ģ
    0.10
    é©°
    0.10
    cy
    0.10
    å°¼æĸ¯
    0.09
    è°IJ
    0.09
    æīª
    0.09
    Activations Density 0.069%

    No Known Activations