© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11024
    Prev
    Next
    INDEX
    Explanations

    coordinates and points

    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
    çĪ·
    -0.08
    æķ´ä¸ª
    -0.07
    rape
    -0.07
    ç½ij
    -0.07
    没æĥ³åĪ°
    -0.06
    计
    -0.06
    å°º
    -0.06
    çŃĸ
    -0.06
    uest
    -0.06
    شة
    -0.06
    POSITIVE LOGITS
     coordinates
    0.09
     koordin
    0.08
    æ²ŁéĢļåįıè°ĥ
    0.08
     combinations
    0.08
     cartesian
    0.08
    amat
    0.08
    èĶĵ
    0.08
    VRT
    0.07
    agus
    0.07
    -coordinate
    0.07
    Activations Density 0.013%

    No Known Activations