© 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. 18234
    Prev
    Next
    INDEX
    Explanations

    superiority comparisons

    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
    è¦ģä¹Īæĺ¯
    -0.09
    æīįè¡Į
    -0.08
    ipas
    -0.08
     Giunta
    -0.08
     subs
    -0.08
    èĪįä¸įå¾Ĺ
    -0.08
    obiet
    -0.08
    åıªä»£è¡¨
    -0.08
    iddy
    -0.08
    åı¯ä»¥æĶ¹åĸĦ
    -0.07
    POSITIVE LOGITS
    ä½ķå¿ħ
    0.07
    è¿IJ
    0.06
    iji
    0.06
    su
    0.06
    nak
    0.06
    reiz
    0.06
    缴æİ¥çĶ¨
    0.06
    kest
    0.06
    ä¸Ģè¡Į
    0.06
     Fach
    0.06
    Activations Density 0.058%

    No Known Activations