© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38618
    Prev
    Next
    INDEX
    Explanations

    website, taxation, laws

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ìį¨
    -0.11
    <|box_end|>
    -0.11
    çŁ¥çļĦ
    -0.11
    æķĻäºİ
    -0.11
    éĥ¨å°±
    -0.10
    çĦ¶å¤§
    -0.10
    æ°§éĩı
    -0.10
    ä¹ĭåıĪ
    -0.10
    ivist
    -0.09
    hle
    -0.09
    POSITIVE LOGITS
    -vous
    0.07
    ми
    0.07
    cheduler
    0.07
    es
    0.07
    Ö¼
    0.07
    ãģĺãĤģãģ¦
    0.06
    çļĦ
    0.06
    Ìģ
    0.06
    Ùĭ
    0.06
    de
    0.06
    Activations Density 0.045%

    No Known Activations