© 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. 50077
    Prev
    Next
    INDEX
    Explanations

    thereby resulting in

    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
    cept
    -0.08
    arte
    -0.08
    inox
    -0.07
    adir
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    arendra
    -0.07
    çİĦ
    -0.07
    avel
    -0.07
    noinspection
    -0.07
     moreover
    -0.07
    POSITIVE LOGITS
    æ¶Ī
    0.08
    ä»ĸ便
    0.08
     indirectly
    0.07
    ä»ĸä¹Łæĺ¯
    0.07
     implicitly
    0.07
    ãģĺãĤģãģ¦
    0.07
    ä»ĸå¿ĥéĩĮ
    0.07
    urch
    0.07
    ij
    0.06
    ä½ķå¿ħ
    0.06
    Activations Density 0.037%

    No Known Activations