© 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. 62911
    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
    usters
    -0.08
    ambi
    -0.07
     libra
    -0.07
    plice
    -0.07
    asser
    -0.07
    ä¸Ģæĥ³
    -0.07
    |h
    -0.06
    eryl
    -0.06
    -AA
    -0.06
     Caleb
    -0.06
    POSITIVE LOGITS
    èĪĴ
    0.07
    _optional
    0.07
    оÑĤе
    0.07
    _elems
    0.06
    çļĦé«ĺ级
    0.06
     comfort
    0.06
    ves
    0.06
    为æĤ£èĢħ
    0.06
    zit
    0.06
    ütt
    0.06
    Activations Density 0.000%

    No Known Activations