© 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. 21293
    Prev
    Next
    INDEX
    Explanations

    customer service and relationship

    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
    elves
    -0.06
    åĬŁ
    -0.06
    æĪIJå°±
    -0.06
    uze
    -0.06
    åħĥ
    -0.06
    FACT
    -0.06
    æī©å®¹
    -0.05
    uste
    -0.05
    ogra
    -0.05
     brag
    -0.05
    POSITIVE LOGITS
    kah
    0.06
    agment
    0.06
    ions
    0.06
    èݱåĿŀ
    0.06
    asting
    0.06
    aden
    0.05
    æĺ¯æŃ£å¸¸çļĦ
    0.05
     везде
    0.05
    ikip
    0.05
     milit
    0.05
    Activations Density 0.003%

    No Known Activations