© 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. 9543
    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
    PosX
    -0.06
    çİ»çĴĥ
    -0.06
     Www
    -0.06
     whereby
    -0.06
     silly
    -0.06
    pseudo
    -0.06
    åĭ¿
    -0.06
     Joaqu
    -0.06
    εÏį
    -0.06
    ños
    -0.06
    POSITIVE LOGITS
    xFFFFFF
    0.08
    éľĸ
    0.08
    ืà¸Ķ
    0.07
    .bd
    0.07
    iskan
    0.07
    tee
    0.07
    afs
    0.07
    gee
    0.07
    سد
    0.06
    ld
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.