© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16080
    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
    ä¸Ģå¤ķ
    -0.08
    naver
    -0.08
    ostra
    -0.07
    haf
    -0.07
    笤
    -0.07
    arit
    -0.07
    ÑģÑĤÑĢи
    -0.07
    åı¤å¸ĮèħĬ
    -0.07
    ÙĪÙĨØ©
    -0.07
     Patr
    -0.07
    POSITIVE LOGITS
    venuto
    0.07
    游æĪıå¹³åı°
    0.07
    èĪĨ
    0.07
    æīĢè½½
    0.07
    atus
    0.07
    éĹ¨å¤´
    0.06
    æĿ¨æ¢ħ
    0.06
    éĩįçĹĩ
    0.06
    åĮĸåıijå±ķ
    0.06
    æİ
    0.06
    Activations Density 0.000%

    No Known Activations