© 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. 46029
    Prev
    Next
    INDEX
    Explanations

    writing skills

    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
    avera
    -0.08
    ãĥįãĤ¿ãĥIJãĥ¬
    -0.07
    ONENT
    -0.07
    åħ¨æĸĩéĺħ读
    -0.07
    ORITY
    -0.07
    pong
    -0.07
    è¿ħ鼷ä¸ĭè½½
    -0.07
    abin
    -0.07
    readcrumb
    -0.07
    Ẩ
    -0.07
    POSITIVE LOGITS
     writing
    0.13
    åĨĻä½ľ
    0.13
    -writing
    0.13
    Writing
    0.13
    åĪĽä½ľ
    0.13
     Writing
    0.12
    writing
    0.12
    åĪĽä½ľçļĦ
    0.12
     drafts
    0.12
    ä½ĵè£ģ
    0.12
    Activations Density 0.204%

    No Known Activations