© 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. 63941
    Prev
    Next
    INDEX
    Explanations

    vague hint

    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
    aylight
    -0.08
     intér
    -0.08
    ä»Ķç»Ĩ
    -0.07
    è´¢æºIJ
    -0.07
    izzo
    -0.07
    ([&
    -0.07
    COPE
    -0.07
    пе
    -0.07
    ä¹īåĭĩ为
    -0.07
    LayoutManager
    -0.07
    POSITIVE LOGITS
    _tp
    0.08
    omo
    0.07
    éĥ¨åĪĨåĨħ容
    0.07
    该åĨħ容
    0.07
    éĻĦåĬł
    0.07
    arov
    0.07
    OTO
    0.07
    éĻĦ带
    0.07
    éĻĦ
    0.07
    åĩĮ
    0.07
    Activations Density 0.006%

    No Known Activations