© 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. 50693
    Prev
    Next
    INDEX
    Explanations

    similarities and shared relationships

    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
    æIJŃéħįçļĦ
    -0.09
    iore
    -0.07
    _RPC
    -0.07
    æIJŃéħį
    -0.07
    rotch
    -0.07
    lord
    -0.07
    éĹ»
    -0.07
    ç¿Ķ
    -0.07
     Leb
    -0.06
     Combination
    -0.06
    POSITIVE LOGITS
    çĽ¸ä¼¼çļĦ
    0.14
    åħ±åIJĮçļĦ
    0.14
    çĽ¸ä¼¼
    0.14
     shared
    0.13
    åħ±äº«
    0.13
    èµĦæºIJåħ±äº«
    0.13
     Shared
    0.13
    shared
    0.12
    Shared
    0.12
     ê³µíĨµ
    0.12
    Activations Density 0.153%

    No Known Activations