© 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. 22052
    Prev
    Next
    INDEX
    Explanations

    expressing desire or intent

    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
    项
    -0.05
     rato
    -0.05
    ä¸įè¦ģåĨį
    -0.05
    ä¸įåĨį
    -0.05
    ç¦
    -0.05
    åij½
    -0.05
    shall
    -0.05
     Cass
    -0.05
    ille
    -0.05
    åį³å°Ĩ
    -0.04
    POSITIVE LOGITS
    缸åħ³æݨèįIJ
    0.07
    hti
    0.07
    occhi
    0.06
    umé
    0.06
     kompat
    0.06
    åĽŀæĿ¥åIJİ
    0.06
    aruh
    0.06
    iscos
    0.06
    èĩ´ä½¿
    0.06
     accurately
    0.06
    Activations Density 0.019%

    No Known Activations