© 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. 21179
    Prev
    Next
    INDEX
    Explanations

    numbers and organization identifiers

    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
    åı£æ°´
    -0.05
    éĻIJ度
    -0.05
    opot
    -0.05
    esome
    -0.05
     elsewhere
    -0.05
    amore
    -0.05
    amá
    -0.05
     presume
    -0.05
     Am
    -0.05
    andie
    -0.05
    POSITIVE LOGITS
    acent
    0.06
     partis
    0.06
    owned
    0.06
     пожал
    0.06
    该类
    0.06
     Partai
    0.05
    olut
    0.05
    ãĤ¿ãĤ¤ãĥĹãģ®
    0.05
    ãģ£ãģį
    0.05
    çªľ
    0.05
    Activations Density 0.050%

    No Known Activations