© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29788
    Prev
    Next
    INDEX
    Explanations

    escape characters and tabs

    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
    thouse
    -0.08
    ymar
    -0.08
    åģıå¿ĥ
    -0.08
    (fabs
    -0.08
    äºĴ为
    -0.07
    ç´¯çļĦ
    -0.07
    ortal
    -0.07
    룸
    -0.07
    zell
    -0.07
    _CBC
    -0.07
    POSITIVE LOGITS
    åįģåħŃ
    0.07
    SID
    0.07
    _FILENAME
    0.07
     Alt
    0.07
     ANSI
    0.06
    éªĩ
    0.06
     sna
    0.06
     hexadecimal
    0.06
     undefined
    0.06
     Mystery
    0.06
    Activations Density 0.060%

    No Known Activations