© 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. 22957
    Prev
    Next
    INDEX
    Explanations

    measures and assessments

    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
    orso
    -0.08
    verse
    -0.07
    åĩıå°ij对
    -0.07
    èĩªèº«é£İéĻ©
    -0.07
    åīįåİ»
    -0.07
    ä¹ĥèĩ³
    -0.07
    à¹Īà¸Ńม
    -0.07
     immortal
    -0.07
    èĹīæѤ
    -0.07
    ious
    -0.06
    POSITIVE LOGITS
    à¸Ĺาà¸ĩ
    0.07
    ellt
    0.07
    lassen
    0.07
     by
    0.07
     from
    0.07
     Libri
    0.06
    ynt
    0.06
    ped
    0.06
     bá
    0.06
    utar
    0.06
    Activations Density 0.111%

    No Known Activations