© 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. 33687
    Prev
    Next
    INDEX
    Explanations

    air and hot gas

    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
     weighing
    -0.08
    æĻ¶ç¡ħ
    -0.07
    éļĪ
    -0.07
    _prec
    -0.07
    åŃ°
    -0.07
    èł
    -0.07
    rick
    -0.07
    æijĩæijĨ
    -0.07
     Doming
    -0.06
    æIJĸ
    -0.06
    POSITIVE LOGITS
     airst
    0.08
    æ°Ķæµģ
    0.08
     Blow
    0.08
     stresses
    0.08
     air
    0.08
     arresting
    0.08
     shocked
    0.08
     blows
    0.08
    åĸī
    0.07
    ç¨
    0.07
    Activations Density 0.001%

    No Known Activations