© 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. 65100
    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
    ulling
    -0.07
    .hw
    -0.07
    agger
    -0.07
    iba
    -0.07
    obo
    -0.07
    ican
    -0.07
    âĨ³
    -0.07
    assis
    -0.07
    éĽķ
    -0.07
    oric
    -0.07
    POSITIVE LOGITS
    çĻ¾åĪĨçĻ¾
    0.08
    æĸ°åĬłåĿ¡
    0.08
    åĬłæĭ¿å¤§
    0.07
     Fazit
    0.07
    à¸ģารศึà¸ģษา
    0.07
    ç»Ŀ对æĺ¯
    0.07
    leh
    0.07
    çļĦ人è¿ĺ
    0.06
    ijin
    0.06
    çĻ¾åĪĨä¹ĭçĻ¾
    0.06
    Activations Density 0.000%

    No Known Activations