© 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. 33319
    Prev
    Next
    INDEX
    Explanations

    impl(ies)

    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
    Ĥ¬
    -0.08
    ¿
    -0.08
    æĺŃ
    -0.07
    raga
    -0.06
    èĽĩ
    -0.06
    为åģļ好
    -0.06
    esis
    -0.06
     vign
    -0.06
    ä½ķ以
    -0.06
    çĭ¡
    -0.06
    POSITIVE LOGITS
    impl
    0.09
    çĶ±æѤ
    0.09
     implies
    0.08
    вле
    0.08
    vah
    0.08
     implying
    0.08
     imply
    0.07
    è¿Ļ对
    0.07
    stadt
    0.07
    å¸Ĥåľºå¯¹
    0.07
    Activations Density 0.013%

    No Known Activations