© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19652
    Prev
    Next
    INDEX
    Explanations

    links in web paths

    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
    LEAR
    -0.07
     teardown
    -0.05
    rove
    -0.05
    æĮĻ
    -0.05
    reach
    -0.05
    illant
    -0.05
    çĥĪ
    -0.05
    cier
    -0.05
    rung
    -0.05
    advance
    -0.05
    POSITIVE LOGITS
    è¿Ļç§į人
    0.07
    ikka
    0.06
    éta
    0.06
     nip
    0.06
    utta
    0.05
    以åIJİåĨį
    0.05
    ẻ
    0.05
    æĹ¥åIJİ
    0.05
    enf
    0.05
    enaar
    0.05
    Activations Density 0.045%

    No Known Activations