© 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. 19956
    Prev
    Next
    INDEX
    Explanations

    data analysis and files

    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
    åIJ¸æĶ¶äºĨ
    -0.05
    ilt
    -0.05
    åIJ¸æĶ¶
    -0.05
     اÙĦØ«
    -0.05
    åħī
    -0.05
    itiers
    -0.05
    æĪĺçķ¥çĽ®æłĩ
    -0.04
    еÑĪ
    -0.04
     gama
    -0.04
    è°Īè¯Ŀ
    -0.04
    POSITIVE LOGITS
    datal
    0.07
    upro
    0.07
    à¹Ģสà¸Ļ
    0.06
     either
    0.06
    åįłåħ¬åı¸
    0.06
    å®ŀéĻħæݧåĪ¶
    0.06
    Either
    0.06
    .handle
    0.06
    agas
    0.06
    ваннÑĭ
    0.06
    Activations Density 0.015%

    No Known Activations