© 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. 7750
    Prev
    Next
    INDEX
    Explanations

    Fat Greek

    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
    aufen
    -0.10
    upe
    -0.09
    atables
    -0.08
    æĬĺä¸į
    -0.08
    eah
    -0.08
    欲滴
    -0.08
    uppe
    -0.08
    omma
    -0.08
    ç±³äºļ
    -0.08
    aip
    -0.07
    POSITIVE LOGITS
    okr
    0.07
    ogram
    0.07
    æ¸
    0.06
    åĵį
    0.06
    åIJ´æ±Ł
    0.06
    åijĬ
    0.06
    åį«åĽ½
    0.06
    izz
    0.06
    cho
    0.06
     tou
    0.06
    Activations Density 0.006%

    No Known Activations