© 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. 47257
    Prev
    Next
    INDEX
    Explanations

    equations and code

    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
    为己任
    -0.06
    åĺĽ
    -0.06
     Seben
    -0.06
    hey
    -0.06
    hein
    -0.06
    å´ĸ
    -0.06
    粪
    -0.06
    ookie
    -0.06
    ernal
    -0.06
    _vid
    -0.06
    POSITIVE LOGITS
    pren
    0.08
    autoload
    0.07
    Ø´Ùĩ
    0.07
    ÑıÑĤа
    0.07
    è¿ĺæľīä¸ĢçĤ¹
    0.07
    legend
    0.07
    utu
    0.07
    _triggered
    0.07
    ayah
    0.07
     opi
    0.07
    Activations Density 0.004%

    No Known Activations