© 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. 34339
    Prev
    Next
    INDEX
    Explanations

    : or ; followed by text

    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
    åī²
    -0.07
    _scope
    -0.07
    以ä¸ĭåĩł
    -0.07
    agai
    -0.06
    indet
    -0.06
    ç¾½
    -0.06
    áĢ¹
    -0.06
    scope
    -0.06
    domain
    -0.06
    æ°ı
    -0.06
    POSITIVE LOGITS
    ahir
    0.08
     Loved
    0.08
    积çĶµ
    0.07
    etails
    0.07
    :error
    0.07
    详ç»ĨçļĦ
    0.07
    etailed
    0.07
     deta
    0.07
    :variables
    0.07
     há»įa
    0.07
    Activations Density 0.005%

    No Known Activations