© 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. 34703
    Prev
    Next
    INDEX
    Explanations

    "just" or "simply" followed by something

    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
    ä¸ĩåħĥå·¦åı³
    -0.08
    åĭĩå¾Ģ缴åīį
    -0.08
    -extra
    -0.08
    els
    -0.08
     accordingly
    -0.07
    æŃ£éģĵ
    -0.07
    getAs
    -0.07
     thầm
    -0.07
    æīĢ称
    -0.07
     abbastanza
    -0.07
    POSITIVE LOGITS
    ç®ĢåįķçļĦ
    0.13
    ç®Ģåįķåľ°
    0.12
    åįķ纯çļĦ
    0.11
    åįķä¸ĢçļĦ
    0.11
    åįķä¸Ģ
    0.11
    满足äºİ
    0.09
     sekedar
    0.09
     mere
    0.09
    åįķ纯
    0.09
     merely
    0.09
    Activations Density 0.056%

    No Known Activations