© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2433
    Prev
    Next
    INDEX
    Explanations

    adultery, unmarried, debts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    ä¸ĩå¤ļ
    -0.29
    èĩ³ä»Ĭ
    -0.28
     millions
    -0.28
    çľĭåĪ°äºĨ
    -0.27
     thousands
    -0.27
    èį£èİ·
    -0.27
    åĪ°çİ°åľ¨
    -0.27
     today
    -0.27
    åIJ¸å¼ķäºĨ
    -0.26
    个å¤ļå°ıæŶ
    -0.26
    POSITIVE LOGITS
    åİŁåĪĻä¸Ĭ
    0.36
    çī¹æ®ĬæĥħåĨµ
    0.33
     unmarried
    0.31
    çĶ·æĸ¹
    0.31
    ä¾Ľåħ»
    0.31
     adultery
    0.31
    ä¸Ģæĸ¹
    0.30
     oneself
    0.30
    责任人
    0.30
     debts
    0.29
    Activations Density 0.018%

    No Known Activations