© 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. 12995
    Prev
    Next
    INDEX
    Explanations

    optical fibers, states, Male, TEM

    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
    iedere
    -0.08
    ÅĤon
    -0.08
    è¿Ļç§įçݰ象
    -0.08
    Inv
    -0.07
     Bris
    -0.07
    ãĤ«ãĥ¼
    -0.07
    allar
    -0.07
    ä½łä¸įè¦ģ
    -0.07
    å¿ĥçIJĨä¸Ĭ
    -0.07
    utnik
    -0.07
    POSITIVE LOGITS
    åīįèĢħ
    0.12
    åIJİèĢħ
    0.10
    ãģĶãģ¨
    0.07
     bzw
    0.07
     respectiv
    0.06
     resp
    0.06
    borg
    0.06
    è¿ĩèĬĤ
    0.06
    elin
    0.06
    è½°
    0.06
    Activations Density 0.516%

    No Known Activations