© 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. 30133
    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
    ÅĤÄĻ
    -0.07
     kenn
    -0.07
    hiba
    -0.07
     Cagliari
    -0.06
    rame
    -0.06
    cede
    -0.06
    ecter
    -0.06
    jonen
    -0.06
    ype
    -0.06
    inke
    -0.06
    POSITIVE LOGITS
    -directory
    0.07
    åį·
    0.07
    ãy
    0.07
    ä½łéĤ£
    0.07
    acci
    0.07
    coup
    0.07
    以ä¸ĬåĨħ容
    0.07
     yourselves
    0.07
    ä¸Ģåį·
    0.07
    é¡·
    0.07
    Activations Density 0.000%

    No Known Activations