© 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. 41011
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    ãĤĦãĤī
    -0.09
    à¸ŀà¸Ń
    -0.08
    .toJSON
    -0.08
    åıĬè¦ģæ±Ĥ
    -0.07
    üns
    -0.07
    wend
    -0.07
    ÄĥrÄĥ
    -0.07
    ãģķãģ¦
    -0.07
    åıĪè¦ģ
    -0.07
     Vidal
    -0.07
    POSITIVE LOGITS
    éķij
    0.07
    éľĢè¦ģ注æĦıçļĦæĺ¯
    0.06
    ãĢĤ
    0.06
    èijĨ
    0.06
    ."
    0.06
     rall
    0.06
    为该
    0.06
    ئÙĥ
    0.06
     discretionary
    0.06
     {*
    0.06
    Activations Density 0.017%

    No Known Activations