© 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. 20784
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    mens
    -0.05
    laget
    -0.05
    -less
    -0.05
    以帮åĬ©
    -0.05
    ä¸ĩå¤ļåħĥ
    -0.05
    æľĢèµ·çłģ
    -0.05
     mene
    -0.05
     futurs
    -0.05
    è¨Ģéģĵ
    -0.05
    éĥ½ä¸įçĶ¨
    -0.05
    POSITIVE LOGITS
    avat
    0.06
     garantiz
    0.06
    et
    0.06
    çĶŁåŃIJ
    0.06
    ourt
    0.05
     crow
    0.05
    ÙĦØ©
    0.05
    uman
    0.05
    ohen
    0.05
     túy
    0.05
    Activations Density 0.004%

    No Known Activations