© 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. 32058
    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
    ä½łåĪ°åºķ
    -0.07
    西åĮº
    -0.07
    jac
    -0.07
    éĺij
    -0.07
    çĽ¹
    -0.07
    æĶ
    -0.07
    éŨå¤ĸ
    -0.07
    æij¸
    -0.06
    exceptions
    -0.06
    è¦ģåĪ°
    -0.06
    POSITIVE LOGITS
    ä¸Ģä¾ĭ
    0.08
    mente
    0.07
    nia
    0.07
    nos
    0.07
    zza
    0.07
    dol
    0.07
     Bytes
    0.07
    pars
    0.07
    .statusCode
    0.07
    agra
    0.07
    Activations Density 0.000%

    No Known Activations