© 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. 31754
    Prev
    Next
    INDEX
    Explanations

    plan, America, Four

    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
    eria
    -0.07
    åįĥåŃĹ
    -0.07
    移
    -0.06
    æĤĦ
    -0.06
    åħĦå¼Ł
    -0.06
    -ng
    -0.06
    igg
    -0.06
    zug
    -0.06
    cu
    -0.06
    èĻ½æĺ¯
    -0.06
    POSITIVE LOGITS
    argar
    0.07
    Enumerator
    0.07
    åĹĵéŁ³
    0.07
    人寿
    0.07
    _FAILURE
    0.07
    imated
    0.07
     Bios
    0.07
    angk
    0.07
    ulen
    0.07
    à¤Ĺर
    0.07
    Activations Density 0.001%

    No Known Activations