© 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. 20015
    Prev
    Next
    INDEX
    Explanations

    referred

    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
    ssä
    -0.06
    ØŃ
    -0.05
    æİ¥åıĹ
    -0.05
    irik
    -0.05
     öff
    -0.05
    åıĬ缸åħ³
    -0.05
    çĶ±è¢«åijĬ
    -0.05
    unik
    -0.05
    sem
    -0.05
    iria
    -0.05
    POSITIVE LOGITS
    åįģåħ¨
    0.06
    иден
    0.06
    ãĤ³ãĥŁ
    0.06
    ächer
    0.06
    OCUS
    0.06
    åľį
    0.06
    ardino
    0.05
    åĽ´
    0.05
    artet
    0.05
    pañ
    0.05
    Activations Density 0.051%

    No Known Activations