© 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. 30837
    Prev
    Next
    INDEX
    Explanations

    software development tools and editing

    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
    æľįåĬ¡èĥ½åĬĽ
    -0.10
    æ¡Īä¾ĭ
    -0.10
    YLE
    -0.09
     каÑĤал
    -0.09
    请èģĶç³»
    -0.09
     Leer
    -0.09
    åĻĻ
    -0.09
    é¨İ
    -0.09
     Gray
    -0.08
    çģ°èī²
    -0.08
    POSITIVE LOGITS
    软件
    0.11
     tools
    0.11
    ç¼ĸè¾ij
    0.11
    å·¥åħ·
    0.10
     software
    0.10
    æİĴ
    0.09
    泯
    0.09
    -edit
    0.09
    .Edit
    0.09
     editing
    0.09
    Activations Density 0.221%

    No Known Activations