© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20145
    Prev
    Next
    INDEX
    Explanations

    max or min values

    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
    沿
    -0.07
    åĩºä¸Ģ个
    -0.06
    åľ°éģĵ
    -0.06
     along
    -0.06
    ungkapkan
    -0.05
    沿çĿĢ
    -0.05
    icle
    -0.05
     Där
    -0.05
    ions
    -0.05
     Along
    -0.05
    POSITIVE LOGITS
     **—
    0.07
    éĢīæĭ©åľ¨
    0.06
    yta
    0.06
    éĽĨåħ¨
    0.06
    ellino
    0.06
    åįıåķĨ解åĨ³
    0.06
    ád
    0.06
    Å¡Äį
    0.06
    taki
    0.06
    лива
    0.06
    Activations Density 0.001%

    No Known Activations