© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48267
    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
    uges
    -0.07
    imed
    -0.07
    ors
    -0.07
    ehn
    -0.07
    ims
    -0.07
    人æ°ijåĮ»éĻ¢
    -0.07
    erre
    -0.07
    å±ħæ°ij身份è¯ģ
    -0.07
    sic
    -0.06
    cone
    -0.06
    POSITIVE LOGITS
    åħ´
    0.07
    ç§ĺ
    0.07
    çĤ¸
    0.07
    çł´
    0.07
    opter
    0.07
     Throwable
    0.07
    ä»Ķ
    0.06
    æı½
    0.06
    zare
    0.06
     agents
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.