© 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. 34642
    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
    itan
    -0.08
    arseille
    -0.08
    ycl
    -0.07
    icot
    -0.07
    çĴ
    -0.07
    çľ·
    -0.07
    yles
    -0.07
    éļ·
    -0.07
    .setChecked
    -0.07
    ToLeft
    -0.07
    POSITIVE LOGITS
    å¢ŀ强ä½ĵè´¨
    0.07
    çĩĥ
    0.07
    ×ŀ×ĵ
    0.06
    æīĵçģ«
    0.06
    inson
    0.06
    ãģ©
    0.06
    abor
    0.06
    ç»ı常æĢ§
    0.06
     Ger
    0.06
    holen
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.