© 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. 20719
    Prev
    Next
    INDEX
    Explanations

    can send

    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
    æĦŁæĥħçļĦ
    -0.06
    аÑĢе
    -0.06
    æī¾åĪ°èĩªå·±
    -0.06
    ä¸įç»ı
    -0.06
    enstein
    -0.06
    enj
    -0.06
    éĢļè¿ĩ以ä¸Ĭ
    -0.06
    mouth
    -0.05
    baugh
    -0.05
    usaha
    -0.05
    POSITIVE LOGITS
    ation
    0.07
    amento
    0.06
    oring
    0.06
    voc
    0.05
    -dess
    0.05
    平平
    0.05
    aring
    0.05
    uration
    0.05
    éķ¿éķ¿
    0.05
    ry
    0.05
    Activations Density 0.017%

    No Known Activations