© 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. 16289
    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
    onia
    -0.07
    ol
    -0.07
    çĮľçĮľ
    -0.06
    odos
    -0.06
     importance
    -0.06
    uitive
    -0.06
     Cop
    -0.06
    æķħ
    -0.06
    usive
    -0.06
    ords
    -0.06
    POSITIVE LOGITS
    hyl
    0.09
    è¦ģä¹Ī
    0.07
    etail
    0.07
     radicale
    0.07
    elu
    0.07
    som
    0.07
    æĽ³
    0.07
    esine
    0.07
    शà¥Ģ
    0.07
    issy
    0.07
    Activations Density 0.000%

    No Known Activations