© 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. 25769
    Prev
    Next
    INDEX
    Explanations

    `(`

    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
    aint
    -0.08
    agner
    -0.07
    ilon
    -0.07
     Tear
    -0.06
    à¸Ńม
    -0.06
    éľ²å¤´
    -0.06
    å°¼æĸ¯
    -0.06
    害
    -0.06
    ç´Ĺ
    -0.06
    quot
    -0.06
    POSITIVE LOGITS
    NSE
    0.08
     ups
    0.08
    ups
    0.07
    onsel
    0.07
    +-+-
    0.07
    éķĩ
    0.07
    ç§ĺ
    0.07
    udging
    0.07
    omos
    0.07
    .getElement
    0.07
    Activations Density 0.005%

    No Known Activations