© 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. 17405
    Prev
    Next
    INDEX
    Explanations

    Scala, Play, Json, sbt

    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
    ç»Ħéķ¿
    -0.10
    ä¾Ħ
    -0.10
    解éĻ¤
    -0.10
    å§Ķ书记
    -0.09
    å¼ķèµ·äºĨ
    -0.09
    åľ¨çİ°åľº
    -0.09
    é³ı
    -0.09
    èıĩ
    -0.08
     Tah
    -0.08
    .CommandType
    -0.08
    POSITIVE LOGITS
    çĥŁçģ«
    0.10
    elps
    0.09
    aper
    0.09
    arris
    0.09
    iy
    0.08
     меÑĢ
    0.08
     fiscal
    0.08
    ulus
    0.08
    _binding
    0.08
    çĤī
    0.08
    Activations Density 0.379%

    No Known Activations