© 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. 4118
    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
    erman
    -0.07
    seite
    -0.06
    _KEYS
    -0.06
     Hughes
    -0.06
    ander
    -0.06
    èģĬ
    -0.06
    ande
    -0.06
    usten
    -0.06
    elman
    -0.06
    èµĦ
    -0.06
    POSITIVE LOGITS
    çī¹èѦ
    0.08
    teri
    0.08
    emap
    0.08
    æij¸äºĨ
    0.08
    imt
    0.08
    iglio
    0.08
    elib
    0.08
    åıĸæ¶Īåħ¶
    0.08
    ä¸IJ
    0.07
    áĥļáĥĶ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.