© 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. 64388
    Prev
    Next
    INDEX
    Explanations

    digits or code counts

    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
    ymar
    -0.08
    èļĬ
    -0.08
    vnÃŃ
    -0.07
    zeug
    -0.07
    VISIBLE
    -0.06
    éĺĸ
    -0.06
    æĿ¥äºº
    -0.06
    åģĩè´§
    -0.06
    åĩºå¤´
    -0.06
    åIJĦ级åIJĦç±»
    -0.06
    POSITIVE LOGITS
    large
    0.08
    大大çļĦ
    0.07
    æłĩåĩĨåĮĸçļĦ
    0.07
    å¤§åľ°éľĩ
    0.07
    åºıåĪĹ
    0.07
    rench
    0.07
    å¾Ī大çļĦ
    0.07
     dico
    0.07
    çħľ
    0.07
     ÑĥÑĢо
    0.07
    Activations Density 0.002%

    No Known Activations