© 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. 19730
    Prev
    Next
    INDEX
    Explanations

    curling up, bundled up, into position

    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
    审议éĢļè¿ĩäºĨ
    -0.07
    pees
    -0.06
    ç³»ç»Łè¿Ľè¡Į
    -0.06
    ÑĤивÑĭ
    -0.06
    zos
    -0.06
    ronym
    -0.06
    ãģ«ãģĶ
    -0.06
     zast
    -0.06
    vido
    -0.06
     preci
    -0.06
    POSITIVE LOGITS
    åİĦ
    0.05
    æĬ±
    0.05
    éĿł
    0.05
    ered
    0.05
    äºĨåĩłåĪĨ
    0.05
    éĻĦ
    0.05
    寸
    0.05
    伯æģ©
    0.05
    ryn
    0.05
    åį«
    0.05
    Activations Density 0.004%

    No Known Activations