© 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. 8002
    Prev
    Next
    INDEX
    Explanations

    initial position or original state

    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
    )__
    -0.08
    ¹Ħ
    -0.08
     >",
    -0.08
     Pris
    -0.08
    iht
    -0.08
    __:
    -0.08
    tte
    -0.08
    æ®ĩ
    -0.08
    ÐŀÐĿ
    -0.08
    edah
    -0.07
    POSITIVE LOGITS
    åİŁæĿ¥çļĦ
    0.14
     original
    0.13
    à¹Ģà¸Ķิม
    0.12
    /original
    0.12
    original
    0.11
    Original
    0.11
    åİŁæľīçļĦ
    0.10
    ãģ«æĪ»
    0.10
     Original
    0.10
    -original
    0.10
    Activations Density 0.094%

    No Known Activations