© 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. 30811
    Prev
    Next
    INDEX
    Explanations

    positive charge

    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
    ä¹ĭ缮çļĦ
    -0.07
    åĽłçĹħ
    -0.07
    å¾Ĵ
    -0.06
    åħ¶èĩªçĦ¶
    -0.06
    ´Ģ
    -0.06
    ä¸Ģ个个
    -0.06
    abbr
    -0.06
    ervised
    -0.06
    æµĭéĩı
    -0.06
    çĥŃ泪
    -0.06
    POSITIVE LOGITS
    akra
    0.08
    spread
    0.08
    æĵ¦å¹²
    0.07
    lessness
    0.07
    éĽĨä¸Ńåľ¨
    0.07
    éĢĴç»Ļ
    0.07
    ä¼łç»Ļ
    0.07
    esel
    0.07
    å¤ľçļĦ
    0.07
    主è¦ģéĽĨä¸Ńåľ¨
    0.07
    Activations Density 0.002%

    No Known Activations