© 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. 30019
    Prev
    Next
    INDEX
    Explanations

    mathematical sets and statements

    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
    ynes
    -0.08
    ´
    -0.07
    æ¸ħæĺİ
    -0.07
    AXB
    -0.07
    paralleled
    -0.07
    wah
    -0.07
    beros
    -0.07
    ciano
    -0.07
    iecz
    -0.07
    ede
    -0.07
    POSITIVE LOGITS
    omy
    0.07
    umpl
    0.07
    urs
    0.07
    ίκ
    0.06
    nden
    0.06
    usting
    0.06
    anken
    0.06
     Fel
    0.06
    åĪ«
    0.06
    åĩĨ
    0.06
    Activations Density 0.038%

    No Known Activations