© 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. 10860
    Prev
    Next
    INDEX
    Explanations

    list of conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    /tasks
    -0.07
    RLF
    -0.07
    γοÏħ
    -0.07
     }]
    -0.07
    è®°å¿Ĩ
    -0.06
    è®°å¿ĨåĬĽ
    -0.06
    è®°å¿ĨéĩĮ
    -0.06
    koop
    -0.06
    itt
    -0.06
     Starter
    -0.06
    POSITIVE LOGITS
    Advertisement
    0.07
    laš
    0.06
    åĬĽéĩı
    0.06
     kolei
    0.06
    vain
    0.06
    åIJĮæĹ¶ä¹Łè¦ģ
    0.06
     gal
    0.06
    alse
    0.06
    åıĪå¦Ĥ
    0.06
    æ®·
    0.06
    Activations Density 0.410%

    No Known Activations