© 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. 28724
    Prev
    Next
    INDEX
    Explanations

    internal, election, majority

    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
    æģ
    -0.08
    agher
    -0.08
    åį¡åľ¨
    -0.07
    lon
    -0.07
    าà¸ĩ
    -0.07
    Bracket
    -0.07
    大éģĵ
    -0.07
    yczy
    -0.07
    phe
    -0.07
    æĮĩå®ļåľ°çĤ¹
    -0.07
    POSITIVE LOGITS
     internal
    0.16
     internally
    0.15
    åĨħéĥ¨
    0.14
    internal
    0.14
     Internal
    0.13
    Internal
    0.13
     internas
    0.13
    _internal
    0.13
     interna
    0.13
     internos
    0.12
    Activations Density 0.413%

    No Known Activations