© 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. 54769
    Prev
    Next
    INDEX
    Explanations

    top of

    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
    OPS
    -0.12
    åıĺæĢģ
    -0.10
    æĬĬæı¡
    -0.09
    ops
    -0.09
    ingo
    -0.09
    é³Ķ
    -0.09
    ucid
    -0.09
    Ops
    -0.09
    çĪ¸å¦Ī
    -0.09
     scale
    -0.08
    POSITIVE LOGITS
    most
    0.11
    ä¸ĬçļĦ
    0.09
    /top
    0.09
    å±ĤéĿ¢
    0.09
    æij¸
    0.08
     mobil
    0.08
    åľ¨é¦Ļ港
    0.08
    顶å±Ĥ
    0.08
    pers
    0.08
    æıŃå¼Ģ
    0.08
    Activations Density 0.050%

    No Known Activations