© 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. 64426
    Prev
    Next
    INDEX
    Explanations

    numbers and code structure

    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
    rix
    -0.07
    ²
    -0.07
    nehmer
    -0.06
    redi
    -0.06
    sey
    -0.06
    RIX
    -0.06
    èĢĮ导èĩ´
    -0.06
    lop
    -0.06
    vron
    -0.06
    åĤĻ
    -0.06
    POSITIVE LOGITS
    onos
    0.08
    åįģäºĮæĮĩ
    0.08
    .:**
    0.08
    å¬Ľ
    0.08
    ł
    0.07
     valer
    0.07
    лÑİби
    0.07
    ÑģовеÑģÑĤ
    0.07
     daraus
    0.07
    ookies
    0.07
    Activations Density 0.013%

    No Known Activations