© 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. 58558
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and their connections

    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
    çŃīéĩįçĤ¹
    -0.08
    åĪĩå®ŀåģļåĪ°
    -0.07
    -ever
    -0.07
    çŃīå¤Ħ
    -0.07
     ÙĦعاÙħ
    -0.07
    deki
    -0.07
    ındaki
    -0.07
    æĪĸåħ¶
    -0.07
    ROID
    -0.07
    ither
    -0.07
    POSITIVE LOGITS
     tersendiri
    0.12
     which
    0.09
     whereby
    0.08
    ä¸į容忽è§Ĩ
    0.08
    ìĸ´ê°Ģ
    0.08
     that
    0.08
     коÑĤоÑĢаÑı
    0.08
    à¸Ĥà¹īà¸Ńมูลà¸Ĺีà¹Ī
    0.08
     اÙĦتÙĬ
    0.07
    æīĢæľª
    0.07
    Activations Density 0.130%

    No Known Activations