© 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. 45610
    Prev
    Next
    INDEX
    Explanations

    code method calls

    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
    мино
    -0.06
    menti
    -0.06
     inter
    -0.06
    uddin
    -0.06
    ottes
    -0.06
    bedarf
    -0.06
     eas
    -0.06
    缸åħ³èµĦ讯
    -0.06
    ç½ijçļĦ
    -0.06
     Brady
    -0.06
    POSITIVE LOGITS
    agio
    0.08
    _internal
    0.08
    avia
    0.08
    _manual
    0.08
    ocab
    0.07
    ä¸ĢæĻĥ
    0.07
    ikian
    0.07
    INTERNAL
    0.07
     Äijiá»ĥn
    0.07
    abin
    0.07
    Activations Density 0.106%

    No Known Activations