© 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. 60289
    Prev
    Next
    INDEX
    Explanations

    amplitude measurement or modulation

    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
    缸è¾ħ缸æĪIJ
    -0.10
    bies
    -0.09
    liness
    -0.08
    féle
    -0.08
    身临åħ¶å¢ĥ
    -0.08
    ieme
    -0.07
    lar
    -0.07
    wards
    -0.07
    ald
    -0.07
    éģĹçĹĩ
    -0.07
    POSITIVE LOGITS
    rary
    0.10
    okka
    0.09
    ovÄĽ
    0.08
    keen
    0.08
    okal
    0.08
    ÄĥrÄĥ
    0.08
    assador
    0.08
    ÅĤyn
    0.08
    uah
    0.08
    ostr
    0.08
    Activations Density 0.010%

    No Known Activations