© 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. 42727
    Prev
    Next
    INDEX
    Explanations

    Ni

    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
    оби
    -0.08
    æļĤè¡Įè§Ħå®ļ
    -0.07
    æĦıä¹ī
    -0.07
    港åı°
    -0.07
    å¸Ĥ
    -0.06
    éĤ
    -0.06
    å¦ĤçĥŁ
    -0.06
    اد
    -0.06
    å®ĺ
    -0.06
    obec
    -0.06
    POSITIVE LOGITS
    ä¹İ
    0.09
    leet
    0.09
    æł¹æį®åħ¶
    0.08
    uD
    0.08
    tones
    0.08
    tet
    0.07
    uÃŁ
    0.07
    ayi
    0.07
    é¢Ĩ导åıĬ
    0.07
    enie
    0.07
    Activations Density 0.001%

    No Known Activations