© 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. 57793
    Prev
    Next
    INDEX
    Explanations

    parental controls

    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
    ç¨Ģ
    -0.10
    åĨ¬
    -0.09
    å®ģ
    -0.09
    积累
    -0.09
    åIJ¹
    -0.09
    诱
    -0.09
    寧
    -0.09
    æĪ´ä¸Ĭ
    -0.09
    iza
    -0.08
    循çݯ
    -0.08
    POSITIVE LOGITS
    家éķ¿
    0.15
    家éķ·
    0.13
    éĿĴå°ijå¹´
    0.13
    管æݧ
    0.12
     parental
    0.11
    对åŃ©åŃIJ
    0.11
    家éķ¿ä»¬
    0.11
    æľªæĪIJ年人
    0.11
    Parent
    0.10
    çļĦ家åºŃ
    0.10
    Activations Density 0.081%

    No Known Activations