© 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. 18304
    Prev
    Next
    INDEX
    Explanations

    "I am a [role]" constructions

    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
    æ±IJ
    -0.06
    ålet
    -0.06
    eken
    -0.05
    -made
    -0.05
     ést
    -0.05
    åĩŃ
    -0.05
     made
    -0.05
    åĭĩæ°Ķ
    -0.05
    баÑĤ
    -0.05
    ÙĨدÙĩ
    -0.05
    POSITIVE LOGITS
    æĪijä»¬çŁ¥éģĵ
    0.06
    adu
    0.06
    imu
    0.06
    inition
    0.06
    truk
    0.06
    è¿Ļæł·çļĦ
    0.05
    çľĭåĪ°è¿Ļ
    0.05
    ASC
    0.05
    åħ·æľīçļĦ
    0.05
    çľĭåĪ°è¿Ļ个
    0.05
    Activations Density 0.008%

    No Known Activations