© 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. 18237
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
    trin
    -0.07
    èĥ½ä»İ
    -0.06
    麻麻
    -0.06
    skich
    -0.06
    IBC
    -0.06
    imits
    -0.06
    stant
    -0.05
    leich
    -0.05
    æĭįäºĨ
    -0.05
    uard
    -0.05
    POSITIVE LOGITS
    æīĢéķ¿
    0.06
     nh
    0.06
    olina
    0.06
    uche
    0.05
    éĿ¢å°į
    0.05
    lem
    0.05
    ÙĦÙĬÙĦ
    0.05
    ech
    0.05
    ä¸Ģ身
    0.05
    ç½ĹæĽ¼
    0.05
    Activations Density 0.017%

    No Known Activations