© 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. 63515
    Prev
    Next
    INDEX
    Explanations

    names and files after keywords

    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
    aines
    -0.07
    åĽłä¸ºåıªæľī
    -0.07
    ApplicationContext
    -0.07
    è¿ľäºĨ
    -0.07
     ë©Ģ리
    -0.07
    _between
    -0.07
    ATING
    -0.07
    ators
    -0.07
    osan
    -0.07
    orgia
    -0.06
    POSITIVE LOGITS
    -default
    0.07
    IAS
    0.07
    ä¸įèµ·çľ¼
    0.07
     Trad
    0.07
    adow
    0.07
    誰ãģ§ãĤĤ
    0.07
     Spiegel
    0.06
    .default
    0.06
    default
    0.06
     assum
    0.06
    Activations Density 0.225%

    No Known Activations