© 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. 18042
    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
    iglio
    -0.06
    cte
    -0.06
    æŃ»ä¸į
    -0.06
     appunto
    -0.06
    Æ¡i
    -0.06
    çĶ¨å®ĥ
    -0.06
    rev
    -0.06
    (*
    -0.06
    带åİ»
    -0.06
     mele
    -0.06
    POSITIVE LOGITS
    {text
    0.08
    ]+'
    0.08
    édi
    0.07
    /connect
    0.07
    ùn
    0.07
    æ¯ĭ庸
    0.07
    LOTS
    0.07
    顾åIJįæĢĿä¹ī
    0.07
    /Button
    0.07
    uci
    0.06
    Activations Density 0.000%

    No Known Activations