© 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. 4559
    Prev
    Next
    INDEX
    Explanations

    Southampton and Sussex

    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
    hythm
    -0.09
    纯åĩĢ
    -0.09
     rem
    -0.09
    -0.09
    å¿ĹæĦ¿
    -0.08
    orm
    -0.08
    ä¹ĭåĨħ
    -0.08
     Mapper
    -0.08
    çĽijçĿ£æ£ĢæŁ¥
    -0.08
    åħ¶æīĢ
    -0.08
    POSITIVE LOGITS
     DRIVER
    0.10
    ÑĢабоÑĤ
    0.09
    ERRY
    0.09
    Ñĩив
    0.09
    kas
    0.09
    _PROVID
    0.09
    åĵı
    0.09
    кÑĥÑĢ
    0.08
    creen
    0.08
    æĽĻ
    0.08
    Activations Density 0.003%

    No Known Activations