© 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. 43740
    Prev
    Next
    INDEX
    Explanations

    school, business, sports, degree, murder

    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
    ampang
    -0.08
    éĤ£ä¹ĪçļĦ
    -0.08
     odr
    -0.07
    é«ĺåĤ²
    -0.07
    .health
    -0.07
    isy
    -0.07
    reck
    -0.07
     Anges
    -0.07
    amah
    -0.07
    InputGroup
    -0.07
    POSITIVE LOGITS
    èĢĮè¨Ģä¹ĭ
    0.07
    uros
    0.07
    EEP
    0.06
    æĮĩ导åѦçĶŁ
    0.06
    è£Ķ
    0.06
    eschi
    0.06
    åĮĸ
    0.06
    lop
    0.06
    ocoa
    0.06
    oure
    0.06
    Activations Density 0.081%

    No Known Activations