© 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. 19341
    Prev
    Next
    INDEX
    Explanations

    content and understanding

    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
     cac
    -0.06
    cac
    -0.06
    æ¿
    -0.06
    gee
    -0.06
    ahn
    -0.06
    aber
    -0.05
     Blonde
    -0.05
    ansi
    -0.05
    Leading
    -0.05
    atoon
    -0.05
    POSITIVE LOGITS
    åĨħ容æĺ¯
    0.05
     content
    0.05
     contenuti
    0.05
    åĨħ容ä¸İ
    0.05
    contents
    0.05
    SURE
    0.05
    åºĶè¿IJèĢĮçĶŁ
    0.05
    åĨħ容
    0.05
    енÑĤа
    0.05
    åĨħ容æľī
    0.05
    Activations Density 0.005%

    No Known Activations