© 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. 18457
    Prev
    Next
    INDEX
    Explanations

    Bomb blast

    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
    apus
    -0.08
    illon
    -0.07
    ogu
    -0.07
    igre
    -0.07
    DataURL
    -0.07
    æĻ¤
    -0.07
    çĵľ
    -0.07
    LBL
    -0.07
    æŀķ
    -0.07
    ä»İè¿ĻéĩĮ
    -0.07
    POSITIVE LOGITS
    ciano
    0.09
    caria
    0.07
    beau
    0.07
    eger
    0.07
    è®©æĽ´å¤ļçļĦ人
    0.07
     à¤ľà¥Īसà¥ĩ
    0.07
    è®©æĽ´å¤ļ人
    0.07
    .registry
    0.07
    åįļ大精深
    0.07
    äºĭ件çļĦ
    0.06
    Activations Density 0.008%

    No Known Activations