© 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. 21815
    Prev
    Next
    INDEX
    Explanations

    possessive followed by a noun

    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
    ergestellt
    -0.07
    ively
    -0.07
    شاÙĨ
    -0.07
    vier
    -0.07
    worthy
    -0.06
    åıĬåħ¶
    -0.06
     **.**
    -0.06
    تÙĬÙĨ
    -0.06
    än
    -0.06
    –and
    -0.06
    POSITIVE LOGITS
    lav
    0.05
    esis
    0.05
     sacco
    0.05
    书
    0.04
    OPA
    0.04
    actice
    0.04
    èĢħ
    0.04
    å¤ļåĩº
    0.04
    isma
    0.04
    åİĭ
    0.04
    Activations Density 0.069%

    No Known Activations