© 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. 8208
    Prev
    Next
    INDEX
    Explanations

    match or coincide

    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
    Ñĸз
    -0.08
    ãĤħãģĨ
    -0.07
    _unused
    -0.07
    ä¸Ńåħ¬
    -0.07
    åľ³
    -0.07
    chester
    -0.07
    yz
    -0.07
    å¼ķãģįç¶ļãģį
    -0.07
    ảnh
    -0.07
    _DI
    -0.07
    POSITIVE LOGITS
     match
    0.10
     matches
    0.09
    åĮ¹éħį
    0.08
     coincide
    0.08
     MATCH
    0.08
    match
    0.08
     Ñģов
    0.08
    Match
    0.08
    åIJ»åIJĪ
    0.08
     actual
    0.08
    Activations Density 0.093%

    No Known Activations