© 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. 43625
    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
    èĨĽ
    -0.07
    ewel
    -0.07
    _DIST
    -0.07
    éĩįè¦ģçļĦäºĭæĥħ
    -0.07
    cesa
    -0.07
     Quite
    -0.06
    tagon
    -0.06
    æľĪåı·
    -0.06
    å¸Ĥè´¢æĶ¿å±Ģ
    -0.06
    quite
    -0.06
    POSITIVE LOGITS
    大æľī
    0.09
    vidia
    0.08
    ữu
    0.08
    å°ıåĪ°
    0.07
    Ú©ÙĪ
    0.07
    ç´
    0.07
    MaxLength
    0.07
    alties
    0.07
    azit
    0.07
    Ùİص
    0.07
    Activations Density 0.000%

    No Known Activations