© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14280
    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
     reconstructed
    -0.07
    isl
    -0.07
    hood
    -0.06
     stir
    -0.06
    l
    -0.06
    ysh
    -0.06
    åĶı
    -0.06
    éĶIJ
    -0.06
    æĸ°ä¸ĸ纪
    -0.06
    orz
    -0.06
    POSITIVE LOGITS
    older
    0.08
    erdem
    0.08
    èĮģ壮
    0.07
    manos
    0.07
    å··
    0.07
     âge
    0.07
    setDisplay
    0.07
    memberof
    0.07
    ToSelector
    0.07
    表åĴĮ
    0.07
    Activations Density 0.000%

    No Known Activations