© 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. 22195
    Prev
    Next
    INDEX
    Explanations

    verb followed by auxiliary or preposition

    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
    ä»įæŧ
    -0.06
    ä¹ĭäºĮ
    -0.06
     ...
    -0.06
     à¸Ļัà¹Īà¸Ļ
    -0.06
    å¤©æľº
    -0.06
     pre
    -0.06
    ç»®
    -0.06
    ...
    -0.06
    eft
    -0.06
    çŁ¥ä¹ĭ
    -0.06
    POSITIVE LOGITS
    å¦Ĥä¸Ĭ
    0.10
    ä¸Ĭè¿°
    0.09
    fera
    0.08
    icarbon
    0.08
    utom
    0.08
    åĩ¶
    0.08
    weichen
    0.08
    iciar
    0.07
    lena
    0.07
    resco
    0.07
    Activations Density 0.001%

    No Known Activations