© 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. 64294
    Prev
    Next
    INDEX
    Explanations

    lift arms carrying

    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
    brig
    -0.09
    baus
    -0.07
    第ä¸Ģ个
    -0.07
    èĤĸ
    -0.07
    zano
    -0.06
    igy
    -0.06
     most
    -0.06
    _Callback
    -0.06
    Ī
    -0.06
    bau
    -0.06
    POSITIVE LOGITS
    æµ·è§Ĵ
    0.08
    idak
    0.08
    OTA
    0.08
    ạch
    0.07
    Ãły
    0.07
    Os
    0.07
     simila
    0.07
     GENERIC
    0.07
    apt
    0.07
    ipot
    0.07
    Activations Density 1.386%

    No Known Activations