© 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. 50980
    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
    没æľīæĥ³åĪ°
    -0.09
    没æĥ³åĪ°
    -0.08
    irn
    -0.07
    ðŁĺĬ
    -0.07
    itta
    -0.07
    зив
    -0.07
    æīĢåľ¨åįķä½į
    -0.06
    å½ĵæŶçļĦ
    -0.06
    åĩīçĪ½
    -0.06
    err
    -0.06
    POSITIVE LOGITS
    ambo
    0.07
    æķ°ä»¥
    0.07
    .truth
    0.07
    ongi
    0.07
    ×Ļ׾×ķת
    0.07
    åĬŁäºİ
    0.07
     tatt
    0.07
    èĩªåĬ©
    0.07
    ikai
    0.07
    ldata
    0.06
    Activations Density 0.000%

    No Known Activations