© 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. 47024
    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
    åijĬåĪ«
    -0.06
     Garrison
    -0.06
    以åĨħ
    -0.06
    ableObject
    -0.06
    emble
    -0.06
    ãģĺãĤģãģ¦
    -0.06
    _bundle
    -0.06
    brace
    -0.06
    çī¹åĪ¥
    -0.06
    尾声
    -0.06
    POSITIVE LOGITS
    é£İäºij
    0.08
    ëł
    0.07
    hini
    0.07
    å°¬
    0.07
    轩
    0.07
    _ISR
    0.07
    ä¸Ĭ课æŶ
    0.07
    趣
    0.07
    contr
    0.07
    ESCO
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.