© 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. 46727
    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
    lod
    -0.07
    ype
    -0.07
     dou
    -0.07
    ä½ĻæĿŃ
    -0.06
    éĴ§
    -0.06
    jab
    -0.06
     stab
    -0.06
    ocat
    -0.06
    (keyword
    -0.06
    tha
    -0.06
    POSITIVE LOGITS
    ÂŃing
    0.08
    å®ħ
    0.07
    ص
    0.07
    åıªåIJ¬
    0.07
    ÂŃt
    0.07
    StrictEqual
    0.07
    ÂŃ
    0.07
    ontos
    0.07
    ÂŃi
    0.07
    å¼ķ
    0.07
    Activations Density 0.000%

    No Known Activations