© 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. 33127
    Prev
    Next
    INDEX
    Explanations

    č true

    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
    è¿Ļä¸ī个
    -0.09
    urn
    -0.08
    è¿Ļä¸ī
    -0.07
    iose
    -0.07
    ä¸īèĢħ
    -0.07
     ketiga
    -0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    ãĢģãĢģ
    -0.07
    _ERR
    -0.07
    ASET
    -0.06
    POSITIVE LOGITS
    åĵģçīĮåĴĮ
    0.09
     chô
    0.08
    avra
    0.08
    Įĵ
    0.07
    gul
    0.07
    åįķä½įåĴĮ个人
    0.07
    į
    0.07
    incer
    0.07
     respiro
    0.07
    illos
    0.07
    Activations Density 0.081%

    No Known Activations