© 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. 21210
    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
    ze
    -0.07
    oren
    -0.07
    ä¸ŃåĽ½æĶ¿åºľ
    -0.07
    hatt
    -0.06
    owned
    -0.06
    atch
    -0.06
    让大家
    -0.06
    纺
    -0.06
    aye
    -0.06
    änge
    -0.06
    POSITIVE LOGITS
    ç¾²
    0.08
    jami
    0.08
    èĭ¦
    0.07
    ï¼Ĭ
    0.07
    严æĺİ
    0.07
     Constr
    0.07
    å¸ĮæľĽèĥ½å¤Ł
    0.07
    ï¼Ĭï¼Ĭ
    0.07
    manent
    0.07
     WON
    0.07
    Activations Density 0.000%

    No Known Activations