© 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. 50102
    Prev
    Next
    INDEX
    Explanations

    water or land vehicles

    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
    éªij车
    -0.07
    æĿ¡çIJĨ
    -0.07
    车çĶ¨
    -0.07
    çĶµåĬ¨èĩªè¡Į车
    -0.07
    ä¸Ĭ车
    -0.07
    åľ¨æ±½è½¦
    -0.07
    éªijèĩªè¡Į车
    -0.07
     aerospace
    -0.06
     Automotive
    -0.06
    ä¸ĭ车
    -0.06
    POSITIVE LOGITS
    è½½
    0.13
    è¼ī
    0.12
    æīĢè½½
    0.12
    çŃī大åŀĭ
    0.11
    满载
    0.10
    è£ħè½½
    0.10
    çŃī设å¤ĩ
    0.10
    åĩºçİ°æķħéļľ
    0.09
    æī¿è½½çĿĢ
    0.09
     carrying
    0.09
    Activations Density 0.289%

    No Known Activations