© 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. 56548
    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
     Äijá»ijc
    -0.08
    èı²å°Ķå¾·
    -0.07
    zijd
    -0.07
    åIJĦéĥ¨
    -0.07
    边走
    -0.07
    ä¸ĢåºĶ俱åħ¨
    -0.07
    çµ®
    -0.07
    èIJ½äºĨ
    -0.07
    人åħ¬åijĬ
    -0.07
    ippers
    -0.07
    POSITIVE LOGITS
    er
    0.09
    own
    0.08
    angga
    0.07
    èĭĹ
    0.07
    edos
    0.06
    RIX
    0.06
    åİŁåij³
    0.06
    obie
    0.06
    rink
    0.06
    wer
    0.06
    Activations Density 0.000%

    No Known Activations