© 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. 48937
    Prev
    Next
    INDEX
    Explanations

    atomic force, nuclei, Scala, age, number

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.12
    ings
    -0.10
    edly
    -0.10
    ãĥ¼ãĤ¸
    -0.09
    æ±Ĥæĺ¯
    -0.08
    ive
    -0.08
    edImage
    -0.08
    ghi
    -0.08
    tings
    -0.08
    GING
    -0.08
    POSITIVE LOGITS
    ÙĬÙĪÙĨ
    0.09
    ity
    0.09
    ly
    0.08
    ally
    0.08
    leveland
    0.07
    ãģªãģĦ
    0.07
    o
    0.07
    bing
    0.07
    ½
    0.07
    yo
    0.07
    Activations Density 0.008%

    No Known Activations