© 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. 15305
    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
    ingan
    -0.08
    éĢIJ
    -0.07
    å¹²åĴ³
    -0.07
     traumatis
    -0.07
    SMART
    -0.06
    jera
    -0.06
    tvr
    -0.06
    ventus
    -0.06
    mented
    -0.06
    .bin
    -0.06
    POSITIVE LOGITS
     Fee
    0.07
    èµĦ
    0.07
    ehn
    0.07
    _SCHEMA
    0.07
    orges
    0.07
    ngle
    0.07
    ()(
    0.07
    åıĭçļĦ
    0.07
     Leder
    0.07
    inch
    0.07
    Activations Density 0.000%

    No Known Activations