© 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. 60357
    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
    ç¢
    -0.09
    çĻ¾åħĥ
    -0.08
    oglio
    -0.08
    ecas
    -0.08
    èѦå®ĺ
    -0.08
    ousand
    -0.07
    даÑĢ
    -0.07
    continu
    -0.07
    anita
    -0.07
    _partitions
    -0.07
    POSITIVE LOGITS
     Ende
    0.06
    åįĬæŃ¥
    0.06
    OMIC
    0.06
     ende
    0.06
    庸
    0.06
     âľ
    0.06
    [out
    0.06
    äºŃäºŃ
    0.06
     noc
    0.06
    çķ¢
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.