© 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. 12299
    Prev
    Next
    INDEX
    Explanations

    quantities of items

    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
    à¦Ĥশ
    -0.07
    aros
    -0.06
    äºĮåįģä¸Ģ
    -0.06
    aped
    -0.06
    enska
    -0.06
     ReturnType
    -0.06
    oved
    -0.06
    anh
    -0.06
    .intent
    -0.06
    æľīæĹł
    -0.06
    POSITIVE LOGITS
    -way
    0.10
    -tier
    0.09
    å±Ĥ次çļĦ
    0.09
    åŁºæľ¬åİŁåĪĻ
    0.08
    å¤ļæľĪ
    0.08
    åıĬ以ä¸Ĭ
    0.08
    ãģ«åĪĨ
    0.08
    -dimensional
    0.07
    次çļĦ
    0.07
    å¤ļæľĪçļĦ
    0.07
    Activations Density 0.770%

    No Known Activations