© 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. 4448
    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
    pac
    -0.08
    å¤ļæīį
    -0.07
    iol
    -0.07
    å¿ĥçĹħ
    -0.07
    yono
    -0.07
    ewan
    -0.07
    ilar
    -0.07
    tuj
    -0.07
    ëıĮ
    -0.07
    rš
    -0.07
    POSITIVE LOGITS
    á»ĭt
    0.08
     uite
    0.07
    uhn
    0.07
    åįķä½įåıĤåĬł
    0.07
    å½ĵæŶ
    0.07
    ราà¸ĩ
    0.07
    IGH
    0.06
    arien
    0.06
    igth
    0.06
    ä¹Ŀåįģ
    0.06
    Activations Density 0.610%

    No Known Activations

    This feature has no known activations.