© 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. 62381
    Prev
    Next
    INDEX
    Explanations

    paragraph or section breaks in formal or technical text.

    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
    åĸľéĹ»
    -0.09
    subcategory
    -0.09
    æł¹æį®å®ŀéĻħæĥħåĨµ
    -0.08
    arend
    -0.08
    reo
    -0.08
    nich
    -0.08
    rance
    -0.07
    acara
    -0.07
    ä»ĸåij½
    -0.07
    -src
    -0.07
    POSITIVE LOGITS
    elist
    0.07
     Clarkson
    0.07
     key
    0.06
     rec
    0.06
     Ze
    0.06
     Lands
    0.06
    Key
    0.06
    继èĢĮ
    0.06
     заÑĤ
    0.06
    key
    0.06
    Activations Density 0.000%

    No Known Activations