© 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. 63931
    Prev
    Next
    INDEX
    Explanations

    US official

    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
    thon
    -0.07
    enci
    -0.07
    aky
    -0.07
    ENC
    -0.07
    ortable
    -0.07
    hev
    -0.07
    å¹´åįİ
    -0.07
     celul
    -0.06
    amber
    -0.06
    amax
    -0.06
    POSITIVE LOGITS
     ÏĥÏħνα
    0.08
    miss
    0.07
    dek
    0.07
    اء
    0.07
    åĴĮéĿŀ
    0.07
    è¿ijåľ¨
    0.07
    çŃīéĿŀ
    0.07
     entw
    0.07
    estra
    0.06
     оÑĢе
    0.06
    Activations Density 0.002%

    No Known Activations