© 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. 55808
    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
    ixa
    -0.08
    ä¸ĵæľī
    -0.07
    %\
    -0.07
    umbuh
    -0.07
    plaintext
    -0.07
    habil
    -0.07
    лла
    -0.07
    angu
    -0.07
    _parts
    -0.06
    Flat
    -0.06
    POSITIVE LOGITS
    enti
    0.08
    otten
    0.08
    èĨĢ
    0.07
    äºĭçļĦ
    0.07
    TRS
    0.07
     applications
    0.07
    owler
    0.06
    人们对
    0.06
    anyl
    0.06
    ent
    0.06
    Activations Density 0.000%

    No Known Activations