© 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. 49139
    Prev
    Next
    INDEX
    Explanations

    (TTAGG)n repeats

    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
     Highlander
    -0.07
    æī¹
    -0.07
    astica
    -0.07
    ansch
    -0.07
     Hatch
    -0.07
    åĽ½å¼º
    -0.07
    ä¸Ģæĸ°
    -0.07
    éĿ©
    -0.07
    operator
    -0.06
    auss
    -0.06
    POSITIVE LOGITS
    bj
    0.07
    å¤ļ线ç¨ĭ
    0.07
    ê¸ī
    0.07
    nje
    0.07
    ('=
    0.07
    ccount
    0.07
    blia
    0.07
     '~/
    0.07
    joj
    0.07
    enom
    0.06
    Activations Density 0.022%

    No Known Activations