© 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. 21452
    Prev
    Next
    INDEX
    Explanations

    names followed by legal case components

    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
    äst
    -0.06
     Dodatk
    -0.06
    luž
    -0.06
    _place
    -0.06
    .vis
    -0.06
    prat
    -0.06
    ä¿¡æĿ¡
    -0.06
     facture
    -0.06
     pauta
    -0.06
    VIS
    -0.06
    POSITIVE LOGITS
     Bew
    0.05
    iega
    0.05
    amarin
    0.05
    åĶ¯
    0.05
    à¤Ĥ
    0.05
    çĿĢæīĭ
    0.05
     Pil
    0.04
     growing
    0.04
    gång
    0.04
     simplex
    0.04
    Activations Density 0.001%

    No Known Activations