© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30118
    Prev
    Next
    INDEX
    Explanations

    .string ", "{: "data", "_id"

    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
    ÙħاÙĦ
    -0.07
    اء
    -0.06
     Ballard
    -0.06
    oso
    -0.06
    ost
    -0.06
     detailed
    -0.06
    ä¼Ļ
    -0.06
    Ø´Ùħ
    -0.06
    çļĦ详ç»Ĩ
    -0.06
    oule
    -0.06
    POSITIVE LOGITS
    &oacute
    0.08
    ersatz
    0.08
    Ī¬
    0.08
    éģ¸äºº
    0.07
    缸åħ³èµĦ讯
    0.07
     Opini
    0.07
    evers
    0.07
    agu
    0.07
    èµĦæĸĻä¸ĭè½½
    0.07
    øv
    0.07
    Activations Density 0.034%

    No Known Activations