© 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. 56657
    Prev
    Next
    INDEX
    Explanations

    client.current, club.length, Task, desc.read

    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
    ippo
    -0.07
     Lass
    -0.07
    家纺
    -0.07
    é²ľ
    -0.07
    /meta
    -0.07
    å°Ĩå°±
    -0.07
    oth
    -0.06
    ruc
    -0.06
    Ral
    -0.06
    çijŀæĭī
    -0.06
    POSITIVE LOGITS
    .launch
    0.07
    ouncer
    0.07
     coronav
    0.07
     عز
    0.07
     íĨµ
    0.07
    ס×ĺ
    0.07
    лип
    0.07
    éĤ¦
    0.07
    iace
    0.07
    åŃIJäºĨ
    0.06
    Activations Density 0.255%

    No Known Activations