© 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. 50486
    Prev
    Next
    INDEX
    Explanations

    family members and parental permission

    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
    峡
    -0.09
    类产åĵģ
    -0.09
    stin
    -0.09
    款
    -0.09
    oken
    -0.09
    ãĤ¸ãĥ£
    -0.09
    zee
    -0.08
     Lane
    -0.08
    åģľä¸ĭ
    -0.08
    çݺ
    -0.08
    POSITIVE LOGITS
    家éķ¿
    0.10
    家éķ¿ä»¬
    0.09
    æĪijå¦Ī
    0.09
    DP
    0.09
    /legal
    0.08
    åIJĦèĩª
    0.08
    4
    0.08
    æĻļé¥Ń
    0.08
    upo
    0.08
    rides
    0.08
    Activations Density 0.057%

    No Known Activations