© 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. 15038
    Prev
    Next
    INDEX
    Explanations

    route A to B, B to A

    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
     favoris
    -0.07
    åľ¨åīįéĿ¢
    -0.07
    amenti
    -0.07
     acabou
    -0.07
    èĬĤåīį
    -0.06
    è·Łåľ¨
    -0.06
    ä¸į对
    -0.06
     forbidden
    -0.06
    çĶ©
    -0.06
    emez
    -0.06
    POSITIVE LOGITS
    infeld
    0.08
    imbra
    0.07
    itaria
    0.07
    å¾·åįİ
    0.07
    ç½ijç«Ļåľ°åĽ¾
    0.07
    åѤç«ĭ
    0.06
    èĥ½åĬ¨
    0.06
    nius
    0.06
    OLO
    0.06
    ä¸ĭ课
    0.06
    Activations Density 0.004%

    No Known Activations