© 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. 47173
    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
    ings
    -0.08
    ocking
    -0.07
    ume
    -0.06
    oje
    -0.06
    æ¶ĪåĮĸ
    -0.06
    åįĥ
    -0.06
    or
    -0.06
    缴æİ¥ä¸İ
    -0.06
    utton
    -0.06
    inds
    -0.06
    POSITIVE LOGITS
     Lesser
    0.09
    kker
    0.08
    stum
    0.08
    æĢ»ä¹¦è®°
    0.08
    ssf
    0.08
    insip
    0.08
    ufs
    0.08
    rés
    0.08
    enner
    0.08
    LBL
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.