© 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. 57333
    Prev
    Next
    INDEX
    Explanations

    ashburn, sign in, aving Douching

    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
    igny
    -0.08
    çĵ¦
    -0.06
     اÙĦØŃج
    -0.06
     Hr
    -0.06
    縮
    -0.06
    minster
    -0.06
    BIN
    -0.06
    nus
    -0.06
     pare
    -0.06
    ència
    -0.06
    POSITIVE LOGITS
    unner
    0.08
    èĭĩ
    0.08
    бли
    0.07
    бки
    0.07
    æĸ§
    0.07
    ddl
    0.07
    bauer
    0.07
    ademia
    0.07
     Fi
    0.07
    belt
    0.07
    Activations Density 0.001%

    No Known Activations