© 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. 50941
    Prev
    Next
    INDEX
    Explanations

    duplicate or same names

    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
    saan
    -0.08
    çī¹æľĹ
    -0.08
    wers
    -0.08
    ObjectContext
    -0.07
    à¸Ńย
    -0.07
     Ayd
    -0.07
    plier
    -0.07
    积æŀģéħįåIJĪ
    -0.07
    gan
    -0.07
    agan
    -0.06
    POSITIVE LOGITS
     overlapping
    0.19
    Duplicate
    0.18
     duplicate
    0.18
     ì¤ijë³µ
    0.18
    duplicate
    0.17
     Duplicate
    0.17
    éĩįåıł
    0.17
     overlap
    0.16
    _duplicate
    0.16
     overlaps
    0.16
    Activations Density 0.271%

    No Known Activations