© 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. 57028
    Prev
    Next
    INDEX
    Explanations

    depending on possibilities

    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
    roud
    -0.08
    ypy
    -0.08
    urrent
    -0.07
    å°¼å°Ķ
    -0.07
    ulumi
    -0.07
    è¶Ĭæĺ¯
    -0.07
    strup
    -0.07
     vét
    -0.07
     Mund
    -0.07
    ä¸Ģåıį
    -0.07
    POSITIVE LOGITS
     depending
    0.09
    depending
    0.07
     dependiendo
    0.07
     dependendo
    0.07
    aum
    0.07
    ieber
    0.07
    odge
    0.07
    ance
    0.06
    æľīåĪ«
    0.06
    wann
    0.06
    Activations Density 0.004%

    No Known Activations