© 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. 19676
    Prev
    Next
    INDEX
    Explanations

    paper, steel, oil, forestry industries

    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
    andar
    -0.06
    ä¸İåIJĪä½ľ
    -0.06
    uhr
    -0.05
     Algar
    -0.05
    otis
    -0.05
    arrant
    -0.05
    æĶ¹éĢł
    -0.05
    宾
    -0.05
    ings
    -0.05
     associ
    -0.05
    POSITIVE LOGITS
    erot
    0.06
    ë¥ĺ
    0.06
    rap
    0.06
    Õ¡Õ£
    0.06
    flags
    0.06
    è½®
    0.05
    å¿ħè¦ģæŶ
    0.05
    rong
    0.05
    kadang
    0.05
    èĬ±å¼ı
    0.05
    Activations Density 0.004%

    No Known Activations