© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6935
    Prev
    Next
    INDEX
    Explanations

    adults or children

    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
    edium
    -0.09
    寡
    -0.09
    iasm
    -0.09
    èįļ
    -0.09
    ç¬ij
    -0.08
    åĪ»
    -0.08
    _ENSURE
    -0.08
    ળ
    -0.08
    èĦ±é¢ĸèĢĮåĩº
    -0.08
    å¾¹
    -0.08
    POSITIVE LOGITS
    æĩĤäºĭ
    0.15
    æĪIJ人
    0.14
    大人
    0.14
    æĪIJ年人
    0.13
     adults
    0.11
     adult
    0.11
    æĪIJçĨŁçļĦ
    0.11
    adult
    0.11
    éķ¿å¤§
    0.11
    俨
    0.10
    Activations Density 0.087%

    No Known Activations