© 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. 40418
    Prev
    Next
    INDEX
    Explanations

    RI CT M ik

    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
    æĢ»æ¯Ķ
    -0.07
    æĸ¯åĿ¦
    -0.07
    ters
    -0.07
    åľ¨é«ĺ
    -0.07
    è·ŁæĪij们
    -0.07
    ãĤ·ãĥ³ãĤ°
    -0.07
    ter
    -0.06
    enstein
    -0.06
    æĴ
    -0.06
    opa
    -0.06
    POSITIVE LOGITS
    cil
    0.08
    uwen
    0.08
    éĵ¿
    0.08
    åį³å°ĨåĪ°æĿ¥
    0.07
    VEN
    0.07
    éĦ
    0.06
    ugia
    0.06
    繫
    0.06
    dif
    0.06
    ucci
    0.06
    Activations Density 0.651%

    No Known Activations