© 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. 43817
    Prev
    Next
    INDEX
    Explanations

    three, points, markers, control, shot, satellites, Dixon

    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
    ksom
    -0.08
    ornos
    -0.08
    imately
    -0.07
    åī¯
    -0.07
    halten
    -0.07
    éªļæī°
    -0.07
    å°ıæĸ°
    -0.07
    osa
    -0.07
    ToSelector
    -0.07
    .addProperty
    -0.07
    POSITIVE LOGITS
     points
    0.09
    å®ļçĤ¹
    0.08
    两çĤ¹
    0.08
    points
    0.07
    çĤ¹
    0.07
    çĤ¹çļĦ
    0.07
     Points
    0.07
    足以
    0.07
     fixing
    0.07
    -point
    0.07
    Activations Density 0.010%

    No Known Activations