© 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. 19070
    Prev
    Next
    INDEX
    Explanations

    solution or program requirements

    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
    å¾ĹçļĦ
    -0.06
    abal
    -0.06
     Conseils
    -0.06
     pos
    -0.06
    kind
    -0.06
    nay
    -0.05
    som
    -0.05
    кÑĥда
    -0.05
    åı·çļĦ
    -0.05
    rol
    -0.05
    POSITIVE LOGITS
     should
    0.06
    æĹ¢è¦ģ
    0.06
    ä¼ļèĩªåĬ¨
    0.06
    ousand
    0.06
    åĬĽæ±Ĥ
    0.05
    ä¸Ģç»ı
    0.05
    isir
    0.05
     ought
    0.05
     must
    0.05
     ideally
    0.05
    Activations Density 0.022%

    No Known Activations