© 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. 3815
    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
    -0.06
    spar
    -0.06
    aci
    -0.06
    å±ħ
    -0.05
     terminated
    -0.05
     cy
    -0.05
    lay
    -0.05
    acie
    -0.05
    o
    -0.05
    庵
    -0.05
    POSITIVE LOGITS
    деле
    0.08
    ÑģовеÑģÑĤ
    0.08
    ContentLoaded
    0.08
     **>>
    0.08
    TriState
    0.08
    #ad
    0.08
    uckets
    0.08
    Ẩ
    0.08
    ivec
    0.08
    TimeInterval
    0.08
    Activations Density 0.000%

    No Known Activations