© 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. 17008
    Prev
    Next
    INDEX
    Explanations

    description or art

    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
    æīĢè¦ģ
    -0.08
    unami
    -0.08
    æīĢåĮħåIJ«
    -0.07
    otov
    -0.07
    ango
    -0.07
    éŨåīį
    -0.07
    å®Ŀå¡Ķ
    -0.07
    æīĢåIJ«
    -0.06
    æł¹æľ¬å°±
    -0.06
    ail
    -0.06
    POSITIVE LOGITS
    noinspection
    0.07
    -command
    0.07
    cer
    0.07
    佬
    0.07
    ver
    0.06
    é«
    0.06
    avers
    0.06
     Hessen
    0.06
    èĭĵ
    0.06
    sc
    0.06
    Activations Density 0.002%

    No Known Activations