© 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. 47565
    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
    ival
    -0.07
     cree
    -0.07
    èĥ±
    -0.07
    allon
    -0.06
    å°¸
    -0.06
    este
    -0.06
    kene
    -0.06
    æĪĸä¸į
    -0.06
    isci
    -0.06
    ä¹Łæĺ¯åįģåĪĨ
    -0.06
    POSITIVE LOGITS
    ÅĤos
    0.08
    ARA
    0.07
    ãĥ©ãĥ³ãĥī
    0.07
    ascus
    0.07
    holm
    0.07
    alum
    0.07
    oard
    0.07
    ylon
    0.07
    èĵī
    0.07
     ilgi
    0.07
    Activations Density 0.000%

    No Known Activations