© 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. 41668
    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
    irmi
    -0.08
    ommer
    -0.08
    irma
    -0.07
    éļ¾æ±Ĥ
    -0.07
    hurst
    -0.07
    cini
    -0.07
    管çIJĨçŃī
    -0.07
    innie
    -0.07
     mee
    -0.07
    /renderer
    -0.07
    POSITIVE LOGITS
    jl
    0.06
     diserta
    0.06
    enu
    0.06
     -
    0.06
    Atl
    0.06
    éĥijéĩį
    0.06
    (?:
    0.05
     kant
    0.05
    adio
    0.05
     suf
    0.05
    Activations Density 0.000%

    No Known Activations