© 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. 47389
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Associates
    -0.07
    ÏĦÏī
    -0.07
    rum
    -0.07
    Äı
    -0.07
    æ¡ĵ
    -0.07
     EINVAL
    -0.07
    abilities
    -0.06
    Ïĥιμο
    -0.06
    षà¥įà¤Ł
    -0.06
    è£
    -0.06
    POSITIVE LOGITS
    ito
    0.08
    irl
    0.08
    qiq
    0.07
    ROTO
    0.07
     unre
    0.07
    acto
    0.07
    Theme
    0.06
    åŃ½
    0.06
    hay
    0.06
    endara
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.