© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17936
    Prev
    Next
    INDEX
    Explanations

    prepared to provide examples

    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
    à¹Ģวียà¸Ļ
    -0.06
    resto
    -0.06
    ØŃاء
    -0.06
    chas
    -0.06
    OOK
    -0.06
    à¸ķรี
    -0.06
    áu
    -0.05
    mos
    -0.05
    ñado
    -0.05
    entemente
    -0.05
    POSITIVE LOGITS
    亮
    0.05
    åıĸä¸ĭ
    0.05
    让å®ĥ
    0.05
    å¸Ī
    0.05
     observ
    0.05
    essen
    0.05
    Õ²
    0.05
    ило
    0.05
    .output
    0.05
    ย
    0.05
    Activations Density 0.001%

    No Known Activations