© 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. 50832
    Prev
    Next
    INDEX
    Explanations

    connecting things with rope or leash

    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
    æķ²
    -0.08
     stacked
    -0.08
    åı°éĺ¶
    -0.07
    åľ°çłĸ
    -0.07
    åıł
    -0.07
    级
    -0.07
    çłĸ
    -0.07
    骨é«ĵ
    -0.07
     surfaces
    -0.07
     stagger
    -0.07
    POSITIVE LOGITS
    绳
    0.15
     tether
    0.14
    绳åŃIJ
    0.14
    繩
    0.14
    绳索
    0.14
     rope
    0.13
    æĭīåĬĽ
    0.13
    çīµå¼ķ
    0.13
     ropes
    0.13
    ç¼ļ
    0.13
    Activations Density 0.396%

    No Known Activations