© 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. 19878
    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
    osphate
    -0.08
    utow
    -0.08
    #w
    -0.07
    çİĦ
    -0.07
    çī¹å°Ķ
    -0.07
    umn
    -0.07
    inheritDoc
    -0.07
    æ±¹
    -0.07
    Orm
    -0.07
    linky
    -0.07
    POSITIVE LOGITS
     Schl
    0.08
    wijk
    0.07
    fyl
    0.07
    kah
    0.07
     fenomeno
    0.06
     phenomenon
    0.06
    singular
    0.06
     Certain
    0.06
    LOTS
    0.06
    ãĥªãĥ¼
    0.06
    Activations Density 0.000%

    No Known Activations