© 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. 1745
    Prev
    Next
    INDEX
    Explanations

    html or mathematical expressions with x

    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
    eltas
    -0.07
    urge
    -0.07
    trum
    -0.07
    ëĦĺ
    -0.07
    DeltaTime
    -0.07
    resher
    -0.07
    LayoutParams
    -0.07
    otel
    -0.07
     onNext
    -0.07
    åįĥå±±
    -0.07
    POSITIVE LOGITS
     gre
    0.07
    .news
    0.07
    VM
    0.06
     Me
    0.06
    kite
    0.06
     Chal
    0.06
    åı«ä½ł
    0.06
     x
    0.06
    ite
    0.06
    ä¸įè¯Ń
    0.06
    Activations Density 0.006%

    No Known Activations