© 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. 30593
    Prev
    Next
    INDEX
    Explanations

    bay/view/hill/street/field/islands/boat

    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
    æŦ
    -0.09
    çħ
    -0.09
    ÑĤеÑĢ
    -0.08
    å¥Ĥ
    -0.08
    èŤ
    -0.08
     ter
    -0.08
    ä¸Ŀä¸Ŀ
    -0.08
    éģ¿
    -0.08
    setData
    -0.07
    cran
    -0.07
    POSITIVE LOGITS
    åIJĮæĥħ
    0.11
    éķ¿èĢģ
    0.10
     desar
    0.10
     vết
    0.09
    èĻ¹
    0.09
    è£ķ
    0.09
    迷失
    0.09
    è¸Ĭ
    0.09
    ä¸įæİĴéĻ¤
    0.09
    zelf
    0.09
    Activations Density 0.013%

    No Known Activations