© 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. 20451
    Prev
    Next
    INDEX
    Explanations

    top, top edges, ethyl, stopwatch, work

    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
    _GENERIC
    -0.08
    临
    -0.07
    itos
    -0.07
    Ł
    -0.07
    绵
    -0.07
    Vect
    -0.06
    幡
    -0.06
    iller
    -0.06
    iggio
    -0.06
     Individ
    -0.06
    POSITIVE LOGITS
    ItemId
    0.08
    à¸Ńาร
    0.07
    没åħ³ç³»
    0.07
    管çIJĨæīĢ
    0.07
    çĪµ
    0.07
    ynes
    0.07
    ä¼ģä¸ļèµĦè´¨
    0.07
    endr
    0.07
    dut
    0.07
    讲æĶ¿æ²»
    0.07
    Activations Density 0.140%

    No Known Activations