© 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. 63560
    Prev
    Next
    INDEX
    Explanations

    passenger compartment or car

    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
    à¸ļาà¸ĩà¸Ńยà¹Īาà¸ĩ
    -0.07
    els
    -0.07
    unting
    -0.07
    icer
    -0.07
    tures
    -0.07
    ãģĺãĤģãģ¦
    -0.07
    _UNDEFINED
    -0.07
    ़
    -0.06
    翼翼
    -0.06
     имени
    -0.06
    POSITIVE LOGITS
    hood
    0.14
    chaft
    0.11
    innen
    0.11
    stvo
    0.11
    -facing
    0.10
    stwo
    0.10
    们çļĦ
    0.10
    Innen
    0.10
    ized
    0.10
    hip
    0.10
    Activations Density 0.306%

    No Known Activations