© 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. 49724
    Prev
    Next
    INDEX
    Explanations

    previous two

    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
    åŁł
    -0.08
     Compte
    -0.07
     targeting
    -0.06
    ote
    -0.06
    iglio
    -0.06
    Ñħло
    -0.06
    Or
    -0.06
    Dependencies
    -0.06
    gericht
    -0.06
     Driver
    -0.06
    POSITIVE LOGITS
    -common
    0.08
    usted
    0.08
     BOTH
    0.08
     обоиÑħ
    0.08
    ยà¸Ļ
    0.08
     entrambe
    0.07
    common
    0.07
    _outer
    0.07
    eway
    0.07
    ToStr
    0.07
    Activations Density 0.059%

    No Known Activations