© 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. 36490
    Prev
    Next
    INDEX
    Explanations

    teenagers and young 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
    roker
    -0.11
    æĴĩ
    -0.10
     ÑĩиÑģле
    -0.09
     bridal
    -0.09
    åģı离
    -0.09
     receipts
    -0.09
    åĨµ
    -0.08
    ksz
    -0.08
    建æĪIJåIJİ
    -0.08
    isoft
    -0.08
    POSITIVE LOGITS
    涯
    0.10
    aged
    0.10
     boy
    0.09
     girl
    0.09
    é«ĺä¸ŃçĶŁ
    0.09
     girls
    0.09
    女åŃ©
    0.09
    AGED
    0.09
     gái
    0.08
    嬴
    0.08
    Activations Density 0.077%

    No Known Activations