© 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. 41880
    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
    ws
    -0.07
    èIJ½
    -0.07
    ç«ĭ
    -0.07
    以åıĬ
    -0.07
    org
    -0.06
    ลา
    -0.06
    è¾ħ
    -0.06
    esm
    -0.06
    allis
    -0.06
    æIJŃ建
    -0.06
    POSITIVE LOGITS
    ITERAL
    0.07
    ä½łè¯´çļĦ
    0.07
    YRO
    0.07
    vore
    0.07
    blement
    0.07
    AGMA
    0.07
    irn
    0.07
    ELD
    0.07
    管æīĢ
    0.07
    /native
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.