© 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. 43393
    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
    rend
    -0.07
    inski
    -0.07
    oppers
    -0.07
    mena
    -0.07
    orte
    -0.07
    yam
    -0.07
    æĶĢ
    -0.07
    èİİæĭī
    -0.07
     tâche
    -0.06
    upt
    -0.06
    POSITIVE LOGITS
    _quote
    0.08
    Ĥ¹
    0.07
     inv
    0.07
    guer
    0.07
    olvable
    0.07
    常è§ĦçļĦ
    0.07
    egov
    0.07
    iace
    0.07
    nicz
    0.07
    ä¼ļæľīå¾Īå¤ļ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.