© 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. 10899
    Prev
    Next
    INDEX
    Explanations

    unincorporated community or census-designated place

    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¸Ģè´¯
    -0.10
    æĥ®
    -0.09
    糧
    -0.09
    æ¤IJ
    -0.09
    StateChanged
    -0.09
    ÑĤи
    -0.09
    åĽ½æĥħ
    -0.09
    åѦä¸ļ
    -0.09
    濯
    -0.09
    对åŃ©åŃIJ
    -0.09
    POSITIVE LOGITS
    _named
    0.10
    çĥĪ
    0.09
    涵
    0.09
    éĢł
    0.09
    åı¯æĥ³èĢĮçŁ¥
    0.08
    irector
    0.08
     Stark
    0.08
     condo
    0.08
    gro
    0.08
    _async
    0.08
    Activations Density 0.482%

    No Known Activations