© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42036
    Prev
    Next
    INDEX
    Explanations

    JSON parsing and serialization

    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
    ASET
    -0.08
    çĬ¹
    -0.07
    itage
    -0.07
    atismo
    -0.07
    è·»
    -0.07
    -pocket
    -0.07
    کرد
    -0.07
    wares
    -0.07
    eldon
    -0.07
    chas
    -0.07
    POSITIVE LOGITS
    gable
    0.07
    able
    0.07
    å°ıåħĶ
    0.07
    lite
    0.07
    thinkable
    0.07
    ä¸Ń人
    0.07
    -compatible
    0.06
    icka
    0.06
    orable
    0.06
    ifiable
    0.06
    Activations Density 0.040%

    No Known Activations