© 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. 3898
    Prev
    Next
    INDEX
    Explanations

    client git pull

    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
    uzz
    -0.07
    angg
    -0.07
    æī¹
    -0.07
    omber
    -0.07
    ubre
    -0.07
    泡
    -0.06
    Ñģловно
    -0.06
    èģĶ
    -0.06
     Lemb
    -0.06
    اÙĦÙĬ
    -0.06
    POSITIVE LOGITS
    åıĬåħ¶
    0.10
    yll
    0.08
    à°¡à±į
    0.08
    дино
    0.08
    åĴĮåħ¶
    0.08
    ==$
    0.07
    매
    0.07
    ('${
    0.07
    enner
    0.07
    ockey
    0.07
    Activations Density 0.179%

    No Known Activations