© 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. 18634
    Prev
    Next
    INDEX
    Explanations

    questions about numbers and specific entities

    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
    urga
    -0.09
    onical
    -0.08
    趣åij³
    -0.08
    keit
    -0.08
    dorf
    -0.08
    è¿Ļ对
    -0.08
    éģĵåħ·
    -0.08
    _TRANSFORM
    -0.08
    ASI
    -0.07
    å±ŀå®ŀ
    -0.07
    POSITIVE LOGITS
    èįª
    0.10
    éĹªè¿ĩ
    0.09
    æĺŁçIJĥ
    0.09
    recur
    0.08
    ers
    0.08
    èĹ¿
    0.08
     setBackgroundColor
    0.08
    建çŃij设计
    0.08
    çĦ±
    0.08
    éŨæĪ·ç½ijç«Ļ
    0.08
    Activations Density 0.015%

    No Known Activations