© 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. 19837
    Prev
    Next
    INDEX
    Explanations

    Turkey Background Early sections

    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
    oun
    -0.06
    [`
    -0.05
    sn
    -0.05
    ——
    -0.05
    踩
    -0.05
    erv
    -0.05
    ook
    -0.05
    and
    -0.05
    ven
    -0.05
    ed
    -0.05
    POSITIVE LOGITS
    alez
    0.06
    phine
    0.06
     ác
    0.06
    Tunes
    0.06
    æĶ¾æĺł
    0.06
    åį«çĶŁåĴĮ
    0.06
    licos
    0.06
    bucks
    0.06
    ãģ£ãģ½
    0.06
    omon
    0.06
    Activations Density 0.167%

    No Known Activations