© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14780
    Prev
    Next
    INDEX
    Explanations

    `is`/`has` followed by predicate

    np_acts-logits-general · gemini-2.5-flash-lite

    sentence or paragraph openings, particularly at the start of new topics or sections.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
    ap
    -0.07
    as
    -0.07
    win
    -0.07
    ur
    -0.06
    cc
    -0.06
    åıª
    -0.06
    éģ
    -0.06
    åħ¶
    -0.06
    andles
    -0.06
    esson
    -0.06
    POSITIVE LOGITS
    egasus
    0.09
    æ³½
    0.09
    ζί
    0.08
    enschap
    0.08
     Guth
    0.08
    ---</
    0.08
    olet
    0.08
    óta
    0.08
    emer
    0.08
    ç½ijåıĭè¯Ħ论
    0.08
    Activations Density 0.022%

    No Known Activations