© 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. 20571
    Prev
    Next
    INDEX
    Explanations

    Linux distributions and software frameworks

    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
    ivan
    -0.07
    ILING
    -0.06
    adesh
    -0.06
    panels
    -0.05
    湿äºĨ
    -0.05
    å°ijäºĨ
    -0.05
    inig
    -0.05
    éĨ
    -0.05
    è
    -0.05
    );$
    -0.05
    POSITIVE LOGITS
    web
    0.06
     Peoples
    0.06
    wap
    0.05
    attack
    0.05
     past
    0.05
    á
    0.05
     hab
    0.05
    貫
    0.05
    åīįä¸Ģ
    0.05
    pl
    0.05
    Activations Density 0.158%

    No Known Activations