© 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. 24373
    Prev
    Next
    INDEX
    Explanations

    size, quantity, distance, measurement

    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
    iya
    -0.09
    ussin
    -0.09
    inari
    -0.08
    undler
    -0.08
    à¹Ħà¸Ĭ
    -0.08
    acas
    -0.08
     killers
    -0.08
    plin
    -0.07
    locks
    -0.07
    comments
    -0.07
    POSITIVE LOGITS
    缸çŃī
    0.08
     size
    0.07
    -sized
    0.07
    大å°ı
    0.07
     sized
    0.07
     equ
    0.07
    å¾Ģè¿Ķ
    0.07
     equal
    0.06
     equivalence
    0.06
    obb
    0.06
    Activations Density 0.002%

    No Known Activations