© 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. 41520
    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
    éĥ½æĺ¯èĩªå·±
    -0.06
    hp
    -0.06
    char
    -0.06
    è¡Ģ
    -0.06
    å¾½
    -0.06
    Gol
    -0.06
    è°Īè°Ī
    -0.06
    antina
    -0.05
    ç¥ŀéĩĩ
    -0.05
    ourse
    -0.05
    POSITIVE LOGITS
    jub
    0.09
    士æŀĹ
    0.08
    ç¾İä¸Ń
    0.08
    urred
    0.08
    eder
    0.08
    .codes
    0.08
    ạ
    0.08
    oby
    0.08
     Leist
    0.08
    uld
    0.07
    Activations Density 0.000%

    No Known Activations