© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19598
    Prev
    Next
    INDEX
    Explanations

    non-volatile

    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
    æĺ¯æĢİä¹ĪåĽŀäºĭ
    -0.06
     kz
    -0.05
    å°±æĺ¯è¿Ļ个
    -0.05
    iddle
    -0.05
     пÑĢиÑģ
    -0.05
    worfen
    -0.05
    viron
    -0.05
     sections
    -0.05
     Knox
    -0.04
    adinya
    -0.04
    POSITIVE LOGITS
    ammad
    0.06
    itos
    0.06
    bod
    0.06
    _THAT
    0.06
    yttä
    0.06
     lijst
    0.06
    ç¿»è¯ijæĪIJ
    0.05
    æºIJèĩª
    0.05
    _YES
    0.05
    çī
    0.05
    Activations Density 0.005%

    No Known Activations