© 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. 1705
    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
    دار
    -0.08
    ç¼¥
    -0.08
     separately
    -0.07
    åħ¶è¡Į为
    -0.07
    ÙĪاÙħ
    -0.07
    credi
    -0.07
    èĩªçĦ¶æĻ¯è§Ĥ
    -0.07
    iswa
    -0.06
     impe
    -0.06
    åıĸæĻ¯
    -0.06
    POSITIVE LOGITS
    éĢĤ度çļĦ
    0.09
    bli
    0.08
    _CONTINUE
    0.07
    ölcs
    0.07
    éĥ¨èIJ½
    0.07
    éĢĤ度
    0.07
    olo
    0.07
    vla
    0.07
    abo
    0.06
    转为
    0.06
    Activations Density 0.000%

    No Known Activations