© 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. 9179
    Prev
    Next
    INDEX
    Explanations

    AA inhibition

    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
    使ä¹ĭ
    -0.07
    ä¹ĭéŃĤ
    -0.07
    Åľ
    -0.07
    оÑģо
    -0.07
     feas
    -0.07
    áĥ¬áĥ§
    -0.07
    çļĦä¸Ģç¬Ķ
    -0.07
    家æĿij
    -0.07
    icana
    -0.06
    ãģŀ
    -0.06
    POSITIVE LOGITS
     Mitra
    0.07
    åį³
    0.07
    pend
    0.07
    ä¸ĩéĩĮ
    0.07
    ileged
    0.07
    åįĥ
    0.07
    tent
    0.06
    ãģĨãģ¡
    0.06
    åįĥåįĥ
    0.06
    ç¿ł
    0.06
    Activations Density 0.008%

    No Known Activations