© 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. 13872
    Prev
    Next
    INDEX
    Explanations

    Allegheny Energy deals

    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
    çĽĺé¾Ļ
    -0.08
    稳
    -0.08
    eden
    -0.08
    acos
    -0.08
    /doc
    -0.08
    estas
    -0.07
    cha
    -0.07
    æī¾ä»ĸ
    -0.07
    -plugins
    -0.07
    å¼Ģæľį
    -0.07
    POSITIVE LOGITS
    atron
    0.08
    ä¸Ńåħ´
    0.07
    åĬłè½½ä¸Ń
    0.06
    ạng
    0.06
    ramework
    0.06
     Trento
    0.06
    igne
    0.06
    à¤Ĺà¥į
    0.06
    ATES
    0.06
    elow
    0.06
    Activations Density 0.033%

    No Known Activations