© 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. 35471
    Prev
    Next
    INDEX
    Explanations

    professions, information, embroiderers

    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
    ä»įå°Ĩ
    -0.09
    éħĭ
    -0.09
    _capability
    -0.09
    æijĦå½±ä½ľåĵģ
    -0.08
    æĢħ
    -0.08
    çĨĬçĮ«
    -0.08
     zipper
    -0.08
    鬣
    -0.08
    æĦŁæħ¨
    -0.08
     Speedway
    -0.08
    POSITIVE LOGITS
    åºķå±Ĥ
    0.10
    å½ĵæŶçļĦ
    0.10
    宫廷
    0.09
    çĿ£
    0.09
    kee
    0.08
    çļĩ家
    0.08
     parchment
    0.08
    俸
    0.08
    scriptions
    0.08
    éĽĨå¸Ĥ
    0.08
    Activations Density 0.167%

    No Known Activations