© 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. 24226
    Prev
    Next
    INDEX
    Explanations

    Standard Model extensions

    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
    lee
    -0.08
    ingan
    -0.08
    çīĻé¾Ī
    -0.08
    ghi
    -0.08
    两åı£
    -0.08
    ’B
    -0.08
    çĮ
    -0.08
    æĹ¥èµ·èĩ³
    -0.08
    stö
    -0.07
    untime
    -0.07
    POSITIVE LOGITS
     arose
    0.07
     arises
    0.07
    èµ·æºIJäºİ
    0.07
    autop
    0.07
    æľ¬è´¨ä¸Ĭ
    0.07
     originated
    0.06
     arise
    0.06
     correspondence
    0.06
    ä¿¡æģ¯çĶ±
    0.06
     emerges
    0.06
    Activations Density 0.087%

    No Known Activations