© 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. 3885
    Prev
    Next
    INDEX
    Explanations

    physical and chemical conditions

    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
    mania
    -0.09
    åİŁæĿ¥
    -0.08
    acker
    -0.07
    æ¯ı次
    -0.07
    teren
    -0.07
    åĪĪ
    -0.07
    åįķ次
    -0.07
    åĬłåħ¥
    -0.07
    oš
    -0.06
    åĬłåħ¥äºĨ
    -0.06
    POSITIVE LOGITS
    ikai
    0.08
    常温
    0.08
    uke
    0.07
     fall
    0.07
    èĻķæĸ¼
    0.07
    λεί
    0.07
    ucc
    0.07
    lick
    0.07
    ç©©
    0.07
    éĥ½å¤Ħäºİ
    0.07
    Activations Density 0.019%

    No Known Activations