© 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. 11367
    Prev
    Next
    INDEX
    Explanations

    peak and structure description

    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
    èIJ¤çģ«
    -0.07
    ãĤŃãĤµ
    -0.07
    OCK
    -0.06
    éļıæĦı
    -0.06
     grant
    -0.06
    quo
    -0.06
    grant
    -0.06
    atico
    -0.06
    мп
    -0.06
    禹
    -0.06
    POSITIVE LOGITS
    æĺİæĺ¾çļĦ
    0.09
    REAK
    0.08
     tajam
    0.08
    è¿Ļæĺ¯çĶ±äºİ
    0.08
    ä¸įæĺİæĺ¾
    0.08
    åĩºçİ°åľ¨
    0.08
     dips
    0.08
    åĪĨæĺİ
    0.08
     peaks
    0.08
    igo
    0.08
    Activations Density 0.075%

    No Known Activations