© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42462
    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
    è°¨æħİ
    -0.07
    atem
    -0.07
    æĺ¾çĿĢ
    -0.07
    rad
    -0.07
    ÅĤow
    -0.07
    haus
    -0.07
    hs
    -0.07
    æ´»çĿĢ
    -0.07
    Rare
    -0.06
    amb
    -0.06
    POSITIVE LOGITS
    Mui
    0.08
    èĬ¬
    0.08
    éķĩéķ¿
    0.08
    صد
    0.08
    ntl
    0.08
    loth
    0.07
    ISC
    0.07
    TeX
    0.07
    afen
    0.07
    npc
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.