© 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. 41432
    Prev
    Next
    INDEX
    Explanations

    per carton

    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
    袤
    -0.07
    _DST
    -0.07
    aye
    -0.07
    åķ¼
    -0.07
    ä¸įéĢļ
    -0.07
    ushman
    -0.07
    neau
    -0.07
     Ribeiro
    -0.06
    åľ¨æīĭ
    -0.06
    éĤĥ
    -0.06
    POSITIVE LOGITS
    ä¸ĩäºĭ
    0.07
    .setContent
    0.07
    wan
    0.07
     "))
    0.07
    غاÙĦ
    0.07
    fp
    0.06
    tru
    0.06
    rophe
    0.06
    ]])
    0.06
    arrass
    0.06
    Activations Density 0.002%

    No Known Activations