© 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. 14161
    Prev
    Next
    INDEX
    Explanations

    look at

    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
    HQ
    -0.08
    çĶļèĩ³æĺ¯
    -0.07
    unning
    -0.07
     blah
    -0.07
    unate
    -0.06
    schau
    -0.06
    ä¸įèĻļ
    -0.06
    ếm
    -0.06
    ä¸Ģå®ļ
    -0.06
    ä»Ģä¹Īéĥ½
    -0.06
    POSITIVE LOGITS
    ìĦ¬
    0.07
    timi
    0.07
    thers
    0.07
    ä¸Ģçľ¼
    0.07
     سرا
    0.07
    _DISABLED
    0.07
    è¿Ļ对
    0.07
    illos
    0.07
    ara
    0.07
    []):
    0.07
    Activations Density 0.014%

    No Known Activations