© 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. 17059
    Prev
    Next
    INDEX
    Explanations

    phrases including "these are"

    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
     gn
    -0.05
    أ
    -0.05
    lastic
    -0.05
     gest
    -0.05
    à¸ĩ
    -0.05
    leve
    -0.05
     ug
    -0.05
    aisse
    -0.05
    路线
    -0.05
     "
    -0.05
    POSITIVE LOGITS
     centrocamp
    0.06
    Äijã
    0.06
    走强
    0.06
    kie
    0.06
     Poco
    0.06
    åĪĿå¤ı
    0.06
    itial
    0.06
    èħ¿éĥ¨
    0.06
    kaz
    0.06
     verfolg
    0.06
    Activations Density 0.008%

    No Known Activations