© 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. 34598
    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
    ibase
    -0.08
    iserie
    -0.08
    _ARB
    -0.08
    ÅĤow
    -0.08
     ÏĥÏħγκ
    -0.08
    èī¯åĵģ
    -0.08
    locker
    -0.08
    éĩı身
    -0.07
    åľ¨æīĢ
    -0.07
     cryptoc
    -0.07
    POSITIVE LOGITS
    æŃ£ç¡®åľ°
    0.07
    ston
    0.06
     intention
    0.06
     transferência
    0.06
     transferring
    0.06
    转移
    0.06
    anus
    0.06
    ialis
    0.06
    æµģåĬ¨
    0.06
     Lair
    0.06
    Activations Density 0.000%

    No Known Activations