© 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. 22931
    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
    ämm
    -0.09
    ÑĥмÑĭ
    -0.08
    θά
    -0.08
    è·¡
    -0.08
    ÑģиÑĤ
    -0.08
    antz
    -0.07
     Pfeffer
    -0.07
    tij
    -0.07
    gul
    -0.07
    :mm
    -0.07
    POSITIVE LOGITS
     adjud
    0.08
    å°Ĭ
    0.07
    obo
    0.07
    èIJ½å®ŀ好
    0.06
    å¼Ģå±ķ好
    0.06
    Multi
    0.06
    ãģĵãģ¨ãģ«
    0.06
    urts
    0.06
    нÑıÑħ
    0.06
     пеÑĢеб
    0.06
    Activations Density 0.000%

    No Known Activations