© 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. 51216
    Prev
    Next
    INDEX
    Explanations

    AMP, acoustic, automation, walker, phase, stir

    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
    åİĦ
    -0.07
    igna
    -0.07
    æĨ¬
    -0.07
    åĨįä¸ī
    -0.06
    رس
    -0.06
    оÑĢÑĤа
    -0.06
    èĥĮ
    -0.06
    娥
    -0.06
    Ĥ¬
    -0.06
     Sop
    -0.06
    POSITIVE LOGITS
    anas
    0.07
    Ñij
    0.07
    öger
    0.07
    amid
    0.07
    mite
    0.07
    mund
    0.07
    èĻ¹
    0.06
    åĴĮåħ¶å®ĥ
    0.06
    èĵ¬èݱ
    0.06
    unte
    0.06
    Activations Density 0.878%

    No Known Activations