© 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. 1797
    Prev
    Next
    INDEX
    Explanations

    quantity, mass, amount

    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
    isle
    -0.07
     mitten
    -0.07
     ((__
    -0.07
    ä¸İ被åijĬ
    -0.07
    itten
    -0.06
    .timing
    -0.06
    åıĸéķ¿è¡¥çŁŃ
    -0.06
    äne
    -0.06
    رش
    -0.06
    inclusive
    -0.06
    POSITIVE LOGITS
     Brilliant
    0.07
    å°ı鬼
    0.07
    htag
    0.07
    è¯Ĩ
    0.07
    ToStr
    0.07
    astia
    0.07
    رات
    0.07
    ãĥŀãĥĪ
    0.07
    IndexOf
    0.06
    apiro
    0.06
    Activations Density 0.002%

    No Known Activations