© 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. 8234
    Prev
    Next
    INDEX
    Explanations

    abilities

    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
    ihan
    -0.07
    ilai
    -0.07
    xcc
    -0.07
    æĿ¨å®¶
    -0.07
    åį¡ç½Ĺ
    -0.07
     cur
    -0.06
    æĺ¾èijĹçļĦ
    -0.06
    далее
    -0.06
    fli
    -0.06
    üst
    -0.06
    POSITIVE LOGITS
    _INCLUDE
    0.07
    ùn
    0.07
    ãģ«ãģĹãģ¦ãĤĤ
    0.07
     Donn
    0.07
    æ¡ĪçĶ±
    0.07
    ä¸įä¼ļåĽłä¸º
    0.06
     Lif
    0.06
    elling
    0.06
    ORLD
    0.06
    _rewrite
    0.06
    Activations Density 0.083%

    No Known Activations