© 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. 21298
    Prev
    Next
    INDEX
    Explanations

    angina pectoris

    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
    å®ļå±ħ
    -0.06
     Gon
    -0.06
    growth
    -0.06
     Somalia
    -0.06
    __',
    -0.06
     gon
    -0.06
     gradu
    -0.06
    å¢ŀéķ¿çİĩ
    -0.06
     growth
    -0.06
    åĩºçĶŁçļĦ
    -0.06
    POSITIVE LOGITS
    å¿ĥèĤĮ
    0.06
    ç¡«
    0.06
     pal
    0.05
    enuine
    0.05
    éĢ¸
    0.05
    ác
    0.05
    èĥ¸çĹĽ
    0.05
    оÑĢод
    0.05
    ä¸įåħħåĪĨ
    0.05
    olina
    0.05
    Activations Density 0.065%

    No Known Activations