© 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. 37824
    Prev
    Next
    INDEX
    Explanations

    Grade, new, or writing

    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
    иÑĢо
    -0.08
    insa
    -0.07
    _inf
    -0.07
    stärke
    -0.07
    agna
    -0.07
    æijĺç¼ĸ
    -0.07
    abi
    -0.07
    aby
    -0.07
    _ASYNC
    -0.07
    inee
    -0.07
    POSITIVE LOGITS
    èĢĮåħ¶ä»ĸ
    0.14
    åħ¶ä½Ļ
    0.12
     whereas
    0.12
     Whereas
    0.09
     ë°ĺë©´
    0.09
     tandis
    0.08
    Otherwise
    0.08
    ä¹Łåıªæľī
    0.08
    éĻ¤æѤ
    0.08
     mÃŃg
    0.08
    Activations Density 0.231%

    No Known Activations