© 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. 49414
    Prev
    Next
    INDEX
    Explanations

    directive, Qube, .0, right, {

    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
    åľĥ
    -0.08
    ×IJר
    -0.07
    abic
    -0.07
    ureau
    -0.07
    åħĭå°Ķ
    -0.07
    ì·¨
    -0.07
    帽
    -0.06
    вика
    -0.06
    acons
    -0.06
    enti
    -0.06
    POSITIVE LOGITS
    ila
    0.07
    åħ´åĽ½
    0.07
    reserve
    0.07
    oria
    0.07
    ://'
    0.07
    itian
    0.07
     XYZ
    0.07
    _RESOLUTION
    0.07
    涼
    0.07
    tlement
    0.07
    Activations Density 0.598%

    No Known Activations