© 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. 25351
    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
    yer
    -0.08
     Coro
    -0.08
    oo
    -0.07
    é«ĺåľ°
    -0.07
    ¿IJ
    -0.07
    ستاÙĨ
    -0.07
    浪
    -0.07
    _PUT
    -0.06
    åĺ±
    -0.06
    以ä¸Ĭæĺ¯
    -0.06
    POSITIVE LOGITS
    pects
    0.08
    MUX
    0.08
    çŀ»
    0.07
    vedi
    0.07
     attent
    0.07
    æī§
    0.07
    ä»İ容
    0.06
    /pm
    0.06
    uly
    0.06
     Gentle
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.