© 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. 43064
    Prev
    Next
    INDEX
    Explanations

    future topics and concepts

    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
    prost
    -0.07
    åĭĩå¾Ģ缴åīį
    -0.07
    Proxy
    -0.07
    好好çļĦ
    -0.07
    åĪ©å®³åħ³ç³»
    -0.07
    ä¿Ĺ称
    -0.07
    顶çĿĢ
    -0.07
    äºĨ大éĩıçļĦ
    -0.07
     followed
    -0.07
    æīİåłĨ
    -0.06
    POSITIVE LOGITS
    åIJįåī¯åħ¶å®ŀ
    0.10
    -ready
    0.08
    èĵĿåĽ¾
    0.08
    åIJįåī¯åħ¶å®ŀçļĦ
    0.08
    ãĤĴ缮æĮĩãģĻ
    0.08
    èĢĮåĬªåĬĽ
    0.08
    ãĤĴ缮æĮĩ
    0.08
    ä¹ĭè·¯
    0.08
     envisioned
    0.08
    建设çļĦ
    0.08
    Activations Density 0.076%

    No Known Activations