© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20847
    Prev
    Next
    INDEX
    Explanations

    crystal display, Persona Arena, acid fermentation, fiber cable, piston pump, Shana III

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sosi
    -0.06
     اÙĦأعÙĦÙī
    -0.06
    aurus
    -0.06
    _EXECUTE
    -0.06
     Territory
    -0.06
    æĴ²
    -0.06
    å¾ĢæľŁåĽŀ顾
    -0.06
    åĨĽåĮº
    -0.06
    åѦéĩij
    -0.06
    éķ·èĢħ
    -0.06
    POSITIVE LOGITS
    æĻ¯
    0.06
    NI
    0.05
    碰
    0.05
    ä¼ĺåħĪ
    0.05
     Conj
    0.05
    éĩĬ
    0.05
    èĦ±ç¦»
    0.05
    ä¸ŃåįĹ
    0.04
    ени
    0.04
    боÑĩ
    0.04
    Activations Density 0.266%

    No Known Activations