© 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. 8609
    Prev
    Next
    INDEX
    Explanations

    code blocks or structured text

    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
    entication
    -0.14
    ampton
    -0.14
    edException
    -0.14
    ness
    -0.12
    edList
    -0.12
    edly
    -0.12
    enticate
    -0.11
    äºĨ对
    -0.11
    äºĨä»ĸ
    -0.11
    ãģ®ãģ¨ãģĵãĤį
    -0.11
    POSITIVE LOGITS
    Ùĩ
    0.21
    an
    0.16
    ãĥ³
    0.16
    u
    0.14
    o
    0.12
    raries
    0.12
    ع
    0.12
    zelfde
    0.12
    ed
    0.12
    ×ķת
    0.11
    Activations Density 0.053%

    No Known Activations