© 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. 49803
    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
    ixin
    -0.09
    èĢģ家
    -0.08
    astique
    -0.08
    uskan
    -0.07
    boro
    -0.07
    otin
    -0.07
    cade
    -0.07
    볨
    -0.07
    åģ¥åº·åĴĮ
    -0.07
    pisode
    -0.07
    POSITIVE LOGITS
    å·§
    0.07
    åį´åıijçİ°
    0.07
    Brand
    0.07
    ifs
    0.07
    /chart
    0.06
    åĵģçīĮ
    0.06
    its
    0.06
    åĵģçīĮä»·åĢ¼
    0.06
    æĬ¢é²ľ
    0.06
    ä½Ĩå®ĥ们
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.