© 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. 24297
    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
    åIJĥæ³ķ
    -0.08
    à¤Ĺत
    -0.08
    å±ĪæĮĩ
    -0.08
    ×ļ
    -0.08
    anmar
    -0.08
    èĢģå¸Ī说
    -0.08
    indra
    -0.07
    æѦéģĵ
    -0.07
    ixels
    -0.07
    æĥ³çŁ¥éģĵçļĦçŃĶæ¡Ī
    -0.07
    POSITIVE LOGITS
    segue
    0.07
    icens
    0.06
    å½Ĵ
    0.06
    èĩªè´Ł
    0.06
    orde
    0.06
    ForResource
    0.06
     maxSize
    0.06
    ä¸Ńèĥ½
    0.06
    tagen
    0.06
    /bus
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.