© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9048
    Prev
    Next
    INDEX
    Explanations

    black hole

    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
    èµ°ä¸ĭåİ»
    -0.08
    arine
    -0.08
    踵
    -0.08
    鬣
    -0.08
    rogen
    -0.08
    kits
    -0.08
    lij
    -0.07
    aré
    -0.07
    oft
    -0.07
    optgroup
    -0.07
    POSITIVE LOGITS
    ä¸įéĢı
    0.08
    /M
    0.07
     equivalent
    0.06
    ifr
    0.06
    åįĬå¾Ħ
    0.06
    unnel
    0.06
    ä¸Ģä¼Ĺ
    0.06
    kek
    0.06
    æģIJ
    0.06
     radius
    0.06
    Activations Density 0.001%

    No Known Activations