© 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. 17132
    Prev
    Next
    INDEX
    Explanations

    rental property and services

    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
    amb
    -0.07
     بدر
    -0.06
    angani
    -0.06
    istic
    -0.06
    asp
    -0.06
     sph
    -0.06
    ä¸Ģãģ¤
    -0.06
    intér
    -0.06
    igno
    -0.06
    ì§Ŀ
    -0.06
    POSITIVE LOGITS
    er
    0.06
    秣
    0.06
    æī¿ç§Ł
    0.05
    ube
    0.05
    erk
    0.05
    Universal
    0.05
    ents
    0.05
    åķ
    0.05
    èIJĿ
    0.05
    ween
    0.05
    Activations Density 0.011%

    No Known Activations