© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64000
    Prev
    Next
    INDEX
    Explanations

    examples followed by clarifying details

    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
    鸳鸯
    -0.08
    èıľ
    -0.07
    Ñıн
    -0.07
    intl
    -0.07
    lagt
    -0.07
    èİ
    -0.07
    NonNull
    -0.07
    åħĦå¼Łä»¬
    -0.07
    Occurred
    -0.07
    åħ³èģĶä¼ģä¸ļ
    -0.07
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.09
    以ä¸ĭåĩł
    0.07
    ä¸įèµ·
    0.07
    ICA
    0.06
    缴æİ¥æĪĸ
    0.06
    ãĢģãĢģ
    0.06
    yme
    0.06
    ìĸ´ëĤĺ
    0.06
    па
    0.06
     pharm
    0.06
    Activations Density 0.503%

    No Known Activations