© 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. 31002
    Prev
    Next
    INDEX
    Explanations

    questioning and requesting

    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
    áºŃy
    -0.09
    aille
    -0.08
    geries
    -0.08
    gau
    -0.08
    Builders
    -0.08
    AndView
    -0.07
    éĹ®é¢ĺæĿ¥äºĨ
    -0.07
    icke
    -0.07
    gev
    -0.07
    .cls
    -0.07
    POSITIVE LOGITS
    å°½åľ¨
    0.06
    /*/
    0.06
    rn
    0.06
    ingan
    0.06
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.06
    \'\
    0.06
    顺便
    0.06
     }\
    0.06
    enia
    0.06
    enny
    0.06
    Activations Density 0.079%

    No Known Activations