© 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. 33545
    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
    reece
    -0.07
     Kore
    -0.07
    accio
    -0.07
    天å®ī
    -0.07
    -bars
    -0.07
    oord
    -0.07
    opsis
    -0.06
    ëį°ìĿ´
    -0.06
    zal
    -0.06
    imba
    -0.06
    POSITIVE LOGITS
    çĴ§
    0.07
    ä¸Ģçľ¼
    0.07
    äºĨä¸Ģçľ¼
    0.07
    urin
    0.07
    ÙĪÙĨÙĬØ©
    0.07
    r
    0.07
    rava
    0.07
    emt
    0.07
     contenuti
    0.07
    ToLower
    0.06
    Activations Density 0.000%

    No Known Activations