© 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. 42866
    Prev
    Next
    INDEX
    Explanations

    <div>č in HTML or code comments</div>

    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
    大ä¸Ń
    -0.08
    oo
    -0.07
    enda
    -0.07
    åŁİ举
    -0.06
    ends
    -0.06
    голо
    -0.06
    çĿĢçļĦ
    -0.06
    æĸĩåĵ²
    -0.06
    æĹłå¤Ħ
    -0.06
     gen
    -0.06
    POSITIVE LOGITS
    åĪ«æıIJ
    0.08
     ÙĪار
    0.08
    çĶľçĶľ
    0.08
    ORI
    0.08
    ationally
    0.08
    anton
    0.08
    lair
    0.07
    aticon
    0.07
    viet
    0.07
     prép
    0.07
    Activations Density 0.220%

    No Known Activations