© 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. 31509
    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
    werks
    -0.07
    åĨįæĬĬ
    -0.07
    alsa
    -0.07
    axter
    -0.07
    æī¬
    -0.07
    aille
    -0.07
    æİĴ骨
    -0.07
    andat
    -0.07
    ellen
    -0.07
    owska
    -0.07
    POSITIVE LOGITS
    ae
    0.07
    ÙĨØ´
    0.07
    øb
    0.07
    失äºĨ
    0.06
    edt
    0.06
     sketch
    0.06
    ly
    0.06
    çĨı
    0.06
     dessins
    0.06
     minim
    0.06
    Activations Density 0.000%

    No Known Activations