© 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. 23391
    Prev
    Next
    INDEX
    Explanations

    metastasis

    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
    ä¸įæīĵ
    -0.08
    .newInstance
    -0.07
    /gpl
    -0.07
    å¹³åľ°
    -0.07
    _NT
    -0.07
    åħ¬åŃĻ
    -0.07
    ters
    -0.07
    /apt
    -0.07
    羡
    -0.06
    以ä¸Ģç§į
    -0.06
    POSITIVE LOGITS
    士
    0.07
    .sections
    0.07
     dang
    0.07
    itr
    0.07
    iju
    0.07
    empl
    0.07
     eet
    0.07
    accia
    0.06
     Sag
    0.06
    åĪĹ
    0.06
    Activations Density 0.002%

    No Known Activations