© 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. 38418
    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
    ยà¹īà¸Ńà¸Ļ
    -0.07
    çºł
    -0.07
    å´İ
    -0.07
     ÐŀбÑĢаÑĤ
    -0.07
     Rang
    -0.07
    Median
    -0.07
    æ®Ĩ
    -0.07
     обÑĢаÑĤ
    -0.07
    reverse
    -0.07
     reverse
    -0.06
    POSITIVE LOGITS
    conds
    0.07
    asset
    0.07
    ModelProperty
    0.07
    iller
    0.07
    åIJİæŀľ
    0.07
    _AVAILABLE
    0.07
    æĪij们åıijçİ°
    0.07
    venes
    0.06
    ä¸Ńåıijçİ°
    0.06
     neut
    0.06
    Activations Density 0.000%

    No Known Activations