© 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. 19648
    Prev
    Next
    INDEX
    Explanations

    information structure

    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
    z
    -0.05
     cl
    -0.05
    åħ¬çĶ¨
    -0.05
     utility
    -0.05
    çıŃä¸Ĭ
    -0.05
    ä¸İ伦
    -0.05
     Har
    -0.05
    ียà¸ļ
    -0.05
    ck
    -0.05
    ngth
    -0.05
    POSITIVE LOGITS
     concess
    0.06
    strup
    0.06
    à¸ķิà¸Ļ
    0.06
    opes
    0.06
    à¸ķà¹īà¸Ļ
    0.06
     Nato
    0.06
     inaug
    0.06
    #w
    0.06
    å°±è§ģ
    0.06
    [id
    0.06
    Activations Density 0.009%

    No Known Activations