© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21968
    Prev
    Next
    INDEX
    Explanations

    flashing, flickering, blinking, twinkling

    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
    ừa
    -0.07
    Ø°ÙĨ
    -0.06
    _fwd
    -0.06
    å½¼æѤ
    -0.06
    æ´»æĢ§åĮĸ
    -0.06
    atin
    -0.06
    ueux
    -0.06
    tracts
    -0.06
    æĢ¥åĪĩ
    -0.06
    ville
    -0.06
    POSITIVE LOGITS
    angan
    0.06
    强çļĦ
    0.06
    orum
    0.05
     chop
    0.05
    icia
    0.05
    жок
    0.05
    ноÑģ
    0.05
    orer
    0.05
    па
    0.05
    stood
    0.05
    Activations Density 0.003%

    No Known Activations