© 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. 31897
    Prev
    Next
    INDEX
    Explanations

    kids, children, teens

    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
     Townsend
    -0.10
    èĿ
    -0.10
    ç¾Į
    -0.09
    å¨ĺ
    -0.09
    è¢ĸ
    -0.09
    uala
    -0.09
    ä¸ĸçķĮåIJĦåĽ½
    -0.09
    èĻļå¼±
    -0.09
     algun
    -0.08
    jiang
    -0.08
    POSITIVE LOGITS
    çĽĸ
    0.12
    åĦ¿ç«¥
    0.10
    èĵĭ
    0.10
    éĿĴå°ijå¹´
    0.10
     childhood
    0.10
     children
    0.09
    (children
    0.09
    åħĴç«¥
    0.09
    .children
    0.08
    (child
    0.08
    Activations Density 0.220%

    No Known Activations