© 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. 19684
    Prev
    Next
    INDEX
    Explanations

    foreign language text

    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
     anywhere
    -0.06
    ula
    -0.06
    —
    -0.05
    atri
    -0.05
     secret
    -0.05
     Chapman
    -0.05
     members
    -0.05
    -
    -0.05
    ts
    -0.05
    åĤ¨èĵĦ
    -0.05
    POSITIVE LOGITS
    磶
    0.07
    è¿Ļç§įæĦŁè§ī
    0.07
     habitu
    0.07
     ervaren
    0.06
    ä¼ļ议强è°ĥ
    0.06
    æ·ĭæ¼ĵå°½
    0.06
    æīĵéĢłæĪIJ为
    0.06
    føl
    0.06
    apel
    0.06
     lá»ĵng
    0.06
    Activations Density 0.004%

    No Known Activations