© 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. 51375
    Prev
    Next
    INDEX
    Explanations

    suggests findings or conclusions

    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
    以为çĦ¶
    -0.07
    é«ĺæĸ°æĬĢæľ¯ä¼ģä¸ļ
    -0.07
    èĤ¯
    -0.07
     Entrev
    -0.07
     Flip
    -0.07
    aging
    -0.07
    å°ıç¼ĸ
    -0.07
    eningen
    -0.07
    ELL
    -0.07
    arc
    -0.07
    POSITIVE LOGITS
    Successfully
    0.07
    æĥ¨
    0.07
    ouve
    0.07
    ä»İä¸Ģ个
    0.07
    èµĦ讯
    0.06
    _plural
    0.06
    以身
    0.06
    ç»Ļæľĭåıĭ
    0.06
    _construct
    0.06
    assis
    0.06
    Activations Density 0.201%

    No Known Activations