© 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. 19273
    Prev
    Next
    INDEX
    Explanations

    Aadhaar card linking

    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
    et
    -0.05
    tritt
    -0.05
     pasa
    -0.05
     offerts
    -0.05
    iante
    -0.05
     diplom
    -0.05
    ç²¾
    -0.05
    åįĹ
    -0.05
     Spatial
    -0.05
     nurs
    -0.05
    POSITIVE LOGITS
    asy
    0.06
    å¦Ĥçģ«
    0.06
     Crow
    0.06
    edale
    0.06
    -form
    0.06
    esy
    0.05
    (KP
    0.05
    displayText
    0.05
    æīĭç»Ń
    0.05
    (CONT
    0.05
    Activations Density 0.011%

    No Known Activations