© 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. 11289
    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
    aglia
    -0.07
    ä¼ij
    -0.07
    vale
    -0.06
    +":
    -0.06
     inde
    -0.06
    estina
    -0.06
    olk
    -0.06
    alang
    -0.06
    æ³ķæĺ¯
    -0.06
    +=(
    -0.06
    POSITIVE LOGITS
    SORT
    0.08
    æ³¢ç½Ĺ
    0.08
    人å±ħ
    0.07
    _SORT
    0.07
    路人
    0.07
    errupt
    0.07
    çĽĸ
    0.07
    ׳×Ļת
    0.07
    à¸Ĺุ
    0.07
    гÑĢе
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.