© 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. 28202
    Prev
    Next
    INDEX
    Explanations

    sequence

    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
    [][
    -0.07
    ·
    -0.06
    alas
    -0.06
    _OP
    -0.06
    åįĬè¾¹
    -0.06
    è¿Ľè¡Įåħ¨éĿ¢
    -0.06
     reprodu
    -0.06
     replic
    -0.06
    allas
    -0.06
    amily
    -0.06
    POSITIVE LOGITS
    ç´§æİ¥çĿĢ
    0.15
    ç´§éļı
    0.12
     sequence
    0.12
    ç´§éĤ»
    0.11
    Sequence
    0.11
    sequence
    0.11
     Sequence
    0.11
    ä¸ŃéĹ´
    0.11
    åºıåĪĹ
    0.10
    è¿ŀç»ŃçļĦ
    0.10
    Activations Density 0.023%

    No Known Activations