© 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. 1825
    Prev
    Next
    INDEX
    Explanations

    expressing gratitude or opinions

    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
    Href
    -0.07
    igsaw
    -0.07
     repu
    -0.07
    atine
    -0.07
    izia
    -0.07
    swer
    -0.07
    BYTES
    -0.06
    veja
    -0.06
    inov
    -0.06
    åħīçݯ
    -0.06
    POSITIVE LOGITS
    表达çļĦ
    0.11
    表达
    0.11
    强çĥĪ
    0.10
    æ·ĭæ¼ĵå°½èĩ´
    0.10
    强çĥĪçļĦ
    0.09
    å¿ĥ声
    0.09
    表达äºĨ
    0.09
    expression
    0.09
    à¸ĸึà¸ĩà¸Ħวาม
    0.09
    表达对
    0.08
    Activations Density 0.053%

    No Known Activations