© 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. 19334
    Prev
    Next
    INDEX
    Explanations

    first time visiter

    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
    elay
    -0.06
    纲è¦ģ
    -0.05
    ä»Ģä¹Īåij¢
    -0.05
    encing
    -0.05
    ger
    -0.05
     ma
    -0.05
     past
    -0.05
     too
    -0.05
    以å¤ĸ
    -0.05
    oid
    -0.05
    POSITIVE LOGITS
    ogos
    0.07
     acom
    0.07
    zá
    0.07
    åijĬ
    0.06
    ovel
    0.06
    lili
    0.06
    atch
    0.06
    новиÑĩ
    0.06
    Known
    0.06
    effectuer
    0.06
    Activations Density 0.004%

    No Known Activations