© 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. 62064
    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°ģ家
    -0.08
    ials
    -0.07
    amer
    -0.07
    anh
    -0.06
     searchable
    -0.06
    å¤ŁäºĨ
    -0.06
    iling
    -0.06
    edly
    -0.06
     requisite
    -0.06
    çľĭä¸įæ¸ħ
    -0.06
    POSITIVE LOGITS
    argo
    0.10
    绾ç»İ
    0.09
    ä¸Ģéģį
    0.08
    remen
    0.08
    èıľé¸Ł
    0.08
    踵
    0.08
    åŃļ
    0.07
    sev
    0.07
    ymes
    0.07
    gorithm
    0.07
    Activations Density 0.000%

    No Known Activations