© 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. 3595
    Prev
    Next
    INDEX
    Explanations

    explaining code or functions

    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
    çĨı
    -0.06
    åħ¼
    -0.06
    è¿İ
    -0.06
    ä¸Ģ段
    -0.06
    arkan
    -0.06
    éĽ¢
    -0.06
    审
    -0.06
    离
    -0.06
    è®°
    -0.06
    ENSIONS
    -0.06
    POSITIVE LOGITS
    åŃ¦ä»¥èĩ´
    0.10
    åĨįçĶ±
    0.08
    æīĢåѦä¸ĵä¸ļ
    0.08
    æµ·éģĵ
    0.08
    зво
    0.08
    QUIRES
    0.08
    ocache
    0.08
    ibert
    0.08
     замо
    0.08
    .bean
    0.08
    Activations Density 0.053%

    No Known Activations