© 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. 45403
    Prev
    Next
    INDEX
    Explanations

    .txt, Carr, P

    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
    貿
    -0.09
    pas
    -0.08
    _META
    -0.08
     bum
    -0.07
    queta
    -0.07
    ç¿Ĵ
    -0.07
    ç¼Ī
    -0.07
    æ¿
    -0.07
    æľ¬æģ¯
    -0.07
    vist
    -0.07
    POSITIVE LOGITS
     again
    0.13
    åĨį次
    0.12
     already
    0.12
    again
    0.12
    already
    0.11
     giÃł
    0.10
     déjÃł
    0.10
    éĩįå¤į
    0.10
     Again
    0.10
    à¸ĭà¹īำ
    0.10
    Activations Density 0.016%

    No Known Activations