© 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. 21617
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs or nouns

    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
    enha
    -0.06
    agner
    -0.06
    åIJĦç§į
    -0.06
    æĮ½
    -0.05
    大éĩıçļĦ
    -0.05
    ifton
    -0.05
    ilmington
    -0.05
    åıijå±ķçļĦ
    -0.05
    RY
    -0.05
    ä¸į
    -0.05
    POSITIVE LOGITS
    egos
    0.06
    _protocol
    0.06
    çŃīä¼ĺåĬ¿
    0.06
    stands
    0.05
    estar
    0.05
    AYER
    0.05
    IDS
    0.05
    jol
    0.05
    ulette
    0.05
     Sue
    0.05
    Activations Density 0.025%

    No Known Activations