© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17301
    Prev
    Next
    INDEX
    Explanations

    leverage or pressure

    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
     Krem
    -0.08
    ä¿Ŀå®Ī
    -0.08
     disp
    -0.07
    oy
    -0.07
    èı²
    -0.07
    tahl
    -0.07
    oyal
    -0.07
     *(*
    -0.06
    å²ļ
    -0.06
    ors
    -0.06
    POSITIVE LOGITS
     preferably
    0.08
    çİĸ
    0.07
    partner
    0.07
     helst
    0.07
    ìĿ´ìĸ´
    0.07
    éľĢè¦ģåħ·å¤ĩ
    0.07
    MouseDown
    0.07
    åĩºäºº
    0.06
    èĩ³å°ijè¦ģ
    0.06
    prefer
    0.06
    Activations Density 0.035%

    No Known Activations