© 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. 17901
    Prev
    Next
    INDEX
    Explanations

    "X wants"

    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
    èĭ¥å¹²éĹ®é¢ĺçļĦ
    -0.07
    çļĦéĤ£ç§į
    -0.07
    ).__
    -0.07
    iegu
    -0.06
     indeed
    -0.06
    ä½ĻåĬĽ
    -0.06
    opot
    -0.06
    ax
    -0.06
    /mac
    -0.06
    ëĭĪëĭ¤
    -0.06
    POSITIVE LOGITS
     Natura
    0.07
    è°ĥæŁ¥åıijçİ°
    0.06
    udies
    0.06
    stit
    0.06
    ullo
    0.06
    ComputedStyle
    0.06
    minster
    0.06
     Lieu
    0.06
    èĢĢ
    0.06
    isku
    0.06
    Activations Density 0.013%

    No Known Activations