© 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. 27630
    Prev
    Next
    INDEX
    Explanations

    mission statement

    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
    é¦ĸä½į
    -0.11
    еÑĩение
    -0.10
    forder
    -0.10
    缯
    -0.10
    é£ĵ
    -0.09
    å¾¼
    -0.09
    isko
    -0.09
    ç¥ĵ
    -0.09
    /upload
    -0.08
    vant
    -0.08
    POSITIVE LOGITS
    使åij½
    0.10
     statement
    0.09
    åĴĮæĬĢæľ¯
    0.09
     mission
    0.09
    æĦŁåĬ¨
    0.09
    åĴĮåıijå±ķ
    0.09
    бÑĥ
    0.08
    éħ¯
    0.08
     Statement
    0.08
    éŀĺ
    0.08
    Activations Density 0.019%

    No Known Activations