© 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. 54960
    Prev
    Next
    INDEX
    Explanations

    browser support or settings

    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
    åĻ¨æ¢°
    -0.09
    éĶ²
    -0.09
     instrumental
    -0.09
    åĻ¨
    -0.09
    è£ħè½½
    -0.09
    ç´łè´¨æķĻèĤ²
    -0.08
     instrumentation
    -0.08
    odon
    -0.08
    å¾Īä½İ
    -0.08
    .addWidget
    -0.08
    POSITIVE LOGITS
    èĢĥéªĮ
    0.09
    ellan
    0.08
    ollen
    0.08
    วà¸ĩศ
    0.08
    æµ¥
    0.08
    桧
    0.08
    aho
    0.08
    ango
    0.08
    stm
    0.07
    .backup
    0.07
    Activations Density 0.004%

    No Known Activations