© 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. 31672
    Prev
    Next
    INDEX
    Explanations

    border with

    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
    âĺĨ
    -0.07
     zaÅĽ
    -0.06
    ).
    -0.06
    èĬ
    -0.06
    ãģĿ
    -0.06
    jel
    -0.06
    )ãĢĤ
    -0.06
     hun
    -0.06
    sville
    -0.06
    ].
    -0.06
    POSITIVE LOGITS
    ä¹ĭæīĢ以
    0.08
     Afgan
    0.07
    å½ķ
    0.07
    æĬ¥è®¯
    0.07
    éĹ®é¢ĺæŶ
    0.07
    ấy
    0.07
    ”—
    0.07
     domestici
    0.07
     Liberties
    0.07
    é«ĺèĢĥæĪIJ绩
    0.07
    Activations Density 0.009%

    No Known Activations