© 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. 2536
    Prev
    Next
    INDEX
    Explanations

    services/information/needed

    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
    VOKE
    -0.09
    å¾Ĺåĩºç»ĵ论
    -0.07
    æĶ¶éĽĨåĴĮ
    -0.07
    _google
    -0.07
    MITTED
    -0.07
    skab
    -0.07
     qil
    -0.07
    ÑħаниÑı
    -0.07
    ToJson
    -0.07
    åħ°è¾¾
    -0.07
    POSITIVE LOGITS
     needed
    0.11
    -needed
    0.11
    æīĢéľĢçļĦ
    0.10
    æĢ¥éľĢ
    0.09
    æīĢéľĢè¦ģçļĦ
    0.09
     necessary
    0.09
    needed
    0.09
    à¹ģà¸ģà¹Ī
    0.09
    ecessary
    0.09
     nodig
    0.08
    Activations Density 0.429%

    No Known Activations