© 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. 19226
    Prev
    Next
    INDEX
    Explanations

    code structure and data formats

    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
    æĸĩ件æĪĸ
    -0.06
    æĤłæĤł
    -0.06
    åĽŃçļĦ
    -0.06
    å·¥ä½ľåĪ¶åº¦
    -0.06
    atina
    -0.06
    awan
    -0.06
    å¥ĩæīį
    -0.05
    ç¾İåĮĸ
    -0.05
    zel
    -0.05
    åĪĽæĸ°åĴĮ
    -0.05
    POSITIVE LOGITS
    antro
    0.06
    éĩ
    0.06
    lsi
    0.06
     ÙĤدر
    0.06
    ä¸Ģ课
    0.05
    cret
    0.05
     including
    0.05
    ity
    0.05
    ä¸Ģä¸Ŀ
    0.05
    XS
    0.05
    Activations Density 0.014%

    No Known Activations