© 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. 27769
    Prev
    Next
    INDEX
    Explanations

    domain and scope

    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
     nhau
    -0.07
    ä¸Ģ头
    -0.07
    æĪĸå°ij
    -0.07
    oref
    -0.07
    /mm
    -0.07
    nemonic
    -0.07
    ä½ĵåĮĸ
    -0.07
    onie
    -0.07
    社
    -0.07
    umbo
    -0.07
    POSITIVE LOGITS
    èĮĥåĽ´
    0.12
    èĮĥåĽ´çļĦ
    0.10
    ç¯Ħåľį
    0.10
     range
    0.10
     restrictions
    0.10
    éĻIJåĪ¶çļĦ
    0.09
    èĮĥåĽ´ä¸º
    0.09
     ranges
    0.09
    èĮĥåĽ´åĨħçļĦ
    0.09
     Range
    0.09
    Activations Density 0.012%

    No Known Activations