© 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. 58412
    Prev
    Next
    INDEX
    Explanations

    living a life or lifestyles

    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
    åIJįæ°Ķ
    -0.10
    æ°ijå¿ĥ
    -0.10
    çŁŃ缺
    -0.09
    éĽĦåİļ
    -0.09
    .named
    -0.09
    aho
    -0.09
    å½Ŀ
    -0.09
    é¢Ī
    -0.09
    å°±ä¸ļ
    -0.08
    å²ļ
    -0.08
    POSITIVE LOGITS
     Heller
    0.11
    å¤ĩ
    0.11
    (high
    0.09
    etro
    0.09
     lifestyle
    0.08
    oz
    0.08
    Away
    0.08
    il
    0.08
    belt
    0.08
    .memo
    0.08
    Activations Density 0.031%

    No Known Activations