© 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. 26355
    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
    ingers
    -0.07
    ovina
    -0.07
    lust
    -0.07
    èĭıéĨĴ
    -0.07
    à´ķàµįà´·
    -0.07
     replica
    -0.06
    ä¾ĭ
    -0.06
    éĩĬ
    -0.06
    aks
    -0.06
    kip
    -0.06
    POSITIVE LOGITS
    FP
    0.07
     hæ
    0.07
    ser
    0.07
    owel
    0.07
    idet
    0.06
    holm
    0.06
    bacher
    0.06
    edom
    0.06
    )","
    0.06
     concept
    0.06
    Activations Density 0.000%

    No Known Activations