© 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. 22663
    Prev
    Next
    INDEX
    Explanations

    cumulative and lifetime measurements

    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
    atsu
    -0.07
    å¤Ħäºİ
    -0.07
    é±
    -0.07
    ipient
    -0.07
     spiked
    -0.07
     immedi
    -0.07
     momentan
    -0.07
    ç´§æĢ¥æĥħåĨµ
    -0.07
    å°ĸéĶIJ
    -0.07
     rejet
    -0.07
    POSITIVE LOGITS
    累积
    0.15
    累计
    0.14
     accumulated
    0.14
     cumulative
    0.14
    cum
    0.13
     accum
    0.13
     duration
    0.12
     Cum
    0.12
     ëĪĦìłģ
    0.12
     cum
    0.11
    Activations Density 0.225%

    No Known Activations