© 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. 31699
    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
    wy
    -0.07
    çIJĨçļĦ
    -0.07
    红衣
    -0.07
    بÙĤ
    -0.07
    headed
    -0.07
    ä¿IJ
    -0.06
    lement
    -0.06
    ell
    -0.06
    ç»ĦåĴĮ
    -0.06
    ured
    -0.06
    POSITIVE LOGITS
    κι
    0.07
    soever
    0.07
    zijd
    0.07
    çľīå¿ĥ
    0.07
    wich
    0.07
    åĭķãģį
    0.07
     <$>
    0.07
    çĭ¬æľī
    0.07
    åįĬå±±
    0.07
    èĽ¤
    0.07
    Activations Density 0.215%

    No Known Activations

    This feature has no known activations.