© 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. 13734
    Prev
    Next
    INDEX
    Explanations

    "-less", "-free", "-independent" suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    agli
    -0.08
    sWith
    -0.08
    åĵī
    -0.08
    ÙĪÙĤ
    -0.08
    nik
    -0.08
    aliza
    -0.08
    olio
    -0.08
    åĴĮåįİ
    -0.08
    ĸī
    -0.08
    以赴
    -0.07
    POSITIVE LOGITS
     Trot
    0.07
    ÑĪенÑĮ
    0.07
    bies
    0.06
    èĢĮæĺ¯
    0.06
    ä¹ĭåıĪ
    0.06
    à¹Ģลย
    0.06
     prin
    0.06
     à¦ıমন
    0.06
    erer
    0.06
    ral
    0.06
    Activations Density 0.174%

    No Known Activations