© 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. 17548
    Prev
    Next
    INDEX
    Explanations

    position in articles or data

    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
    ä¸įè¿ĩè¿Ļ
    -0.05
     kennis
    -0.05
    itures
    -0.05
    åŁºéĩijä¼ļ
    -0.05
    راد
    -0.05
    ium
    -0.05
    æĿ¯æ°´
    -0.05
     //(
    -0.05
    ساسÙĬØ©
    -0.05
    arnya
    -0.05
    POSITIVE LOGITS
    wick
    0.07
    ä¼ĺèĥľ
    0.06
    mey
    0.06
     dosp
    0.06
    è¯ī
    0.06
    UAL
    0.06
     trial
    0.06
    trial
    0.06
    wann
    0.05
    istr
    0.05
    Activations Density 0.001%

    No Known Activations