© 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. 48947
    Prev
    Next
    INDEX
    Explanations

    finding solutions or information

    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
    /XML
    -0.09
    æµĥ
    -0.09
    åı°ä¸Ĭ
    -0.08
    iesta
    -0.08
    ä»İæĿ¥ä¸į
    -0.08
    etch
    -0.08
     TOOL
    -0.08
    æ¶Ŀ
    -0.08
    è§ģè¿ĩ
    -0.08
    (del
    -0.08
    POSITIVE LOGITS
    踪
    0.13
    OrCreate
    0.11
    åIJĪéĢĤçļĦ
    0.11
    åħ±é¸£
    0.10
    碴
    0.10
    èĮ¬
    0.10
    ä¹IJ趣
    0.10
    çªģçł´åı£
    0.10
    amental
    0.10
    åIJĪéĢĤ
    0.10
    Activations Density 0.352%

    No Known Activations