© 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. 64793
    Prev
    Next
    INDEX
    Explanations

    direction or movement words

    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
    åİ»åIJ§
    -0.08
    å¿ĥæĥ³äºĭæĪIJ
    -0.07
    座çļĦ
    -0.07
    fromJson
    -0.07
    ç«ĭåľ¨
    -0.07
    åĪĻå°Ĩ
    -0.07
    å·²ç»ıä»İ
    -0.07
    LEASE
    -0.06
    å¹¼å°ı
    -0.06
    __))
    -0.06
    POSITIVE LOGITS
    åĨįåĪ°
    0.11
    iente
    0.08
     onwards
    0.08
    ãģ«ãģĭãģijãģ¦
    0.08
     onward
    0.08
     ÙĪØŃتÙī
    0.07
     toward
    0.07
    åĪ°èĢģ
    0.07
    epak
    0.07
    ä¸Ģ缴åĪ°
    0.07
    Activations Density 0.015%

    No Known Activations