© 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. 34529
    Prev
    Next
    INDEX
    Explanations

    numbered lists with ranking

    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
    enko
    -0.07
    reif
    -0.07
    aina
    -0.07
    inqu
    -0.07
     à¸Ĭม
    -0.07
    eneg
    -0.07
    afka
    -0.07
    :bold
    -0.06
    /facebook
    -0.06
    饶
    -0.06
    POSITIVE LOGITS
     davon
    0.07
    åį·
    0.06
    <|repo_name|>
    0.06
    çĭ¸
    0.06
    Colle
    0.06
    ÑĢа
    0.06
    vÄĽ
    0.06
    éŨå°Ĩ
    0.06
    lijke
    0.06
    ólog
    0.06
    Activations Density 0.008%

    No Known Activations