© 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. 17111
    Prev
    Next
    INDEX
    Explanations

    extra or unnecessary content

    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
    eny
    -0.08
    _formats
    -0.07
    spell
    -0.07
    schlä
    -0.07
     discontin
    -0.07
    สำ
    -0.07
    _sign
    -0.07
    ä¸įåħħåĪĨ
    -0.07
    undy
    -0.07
    cados
    -0.07
    POSITIVE LOGITS
    é¢Ŀå¤ĸçļĦ
    0.13
    é¢Ŀå¤ĸ
    0.13
     extra
    0.13
    å¤ļä½ĻçļĦ
    0.11
    å¤ļä½Ļ
    0.11
     unnecessary
    0.11
    extra
    0.10
    éĻĦåĬł
    0.10
     additional
    0.10
    ä¸įå¿ħè¦ģçļĦ
    0.10
    Activations Density 0.038%

    No Known Activations