© 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. 31965
    Prev
    Next
    INDEX
    Explanations

    batting statistics

    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
    éħįä¸Ĭ
    -0.08
    _]
    -0.07
    åı¶
    -0.06
     vez
    -0.06
    اØŃت
    -0.06
     pio
    -0.06
    ög
    -0.06
    ÙĪجÙĩ
    -0.06
     pairing
    -0.06
     Infragistics
    -0.06
    POSITIVE LOGITS
    çħ¦
    0.08
    миÑĤ
    0.07
    box
    0.07
     prescribed
    0.07
    _fid
    0.07
    平平
    0.07
    æIJĶ
    0.07
    ola
    0.07
    олÑĮ
    0.07
    åĪĿå§ĭ
    0.07
    Activations Density 0.053%

    No Known Activations