© 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. 42008
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    entak
    -0.09
    èĩªåĬĽ
    -0.08
    å¾Ĵæīĭ
    -0.08
    临éŨ
    -0.07
    ilta
    -0.07
    çŃīä»Ģä¹Ī
    -0.07
     barring
    -0.07
    ibrated
    -0.07
    indrome
    -0.07
    好人
    -0.07
    POSITIVE LOGITS
    craft
    0.07
    sled
    0.07
    Mi
    0.07
    awl
    0.07
    ãĥ£
    0.07
     ÙĨاÙĤ
    0.07
    å¾ĢæľŁåĽŀ顾
    0.07
    大çīĩ
    0.06
    roit
    0.06
    guas
    0.06
    Activations Density 0.000%

    No Known Activations