© 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. 25641
    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
     abr
    -0.07
    åĽ±
    -0.07
    ruits
    -0.07
    æĹŃæĹ¥
    -0.07
    è¾¾æĸ¯
    -0.06
    akkan
    -0.06
     (?)
    -0.06
    åĪĨæ°´
    -0.06
    å°ĸ
    -0.06
    ione
    -0.06
    POSITIVE LOGITS
    allar
    0.08
    éĦĻ
    0.08
    alyzer
    0.08
    .exports
    0.07
    itys
    0.07
    ãģĭãĤĬ
    0.07
    .host
    0.07
    hofer
    0.07
    ostante
    0.07
    emaker
    0.07
    Activations Density 0.000%

    No Known Activations