© 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. 12581
    Prev
    Next
    INDEX
    Explanations

    for followed by usage/recipient

    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
    ekar
    -0.07
    acet
    -0.07
    erset
    -0.07
    teken
    -0.07
    ouser
    -0.07
    aviolet
    -0.07
    åı¯åĪ©çĶ¨
    -0.07
    èĩªå·±çļĦåĬªåĬĽ
    -0.06
    lodash
    -0.06
     suatu
    -0.06
    POSITIVE LOGITS
    åĪĿåѦèĢħ
    0.09
     beginners
    0.09
    æľīçī¹æ®Ĭ
    0.08
     Ñĥме
    0.08
     purposes
    0.08
    å¤ĦçIJĨ
    0.08
     situations
    0.08
    ummer
    0.08
     emergencies
    0.08
     ÙĪÙĦÙĦ
    0.08
    Activations Density 0.524%

    No Known Activations