© 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. 16946
    Prev
    Next
    INDEX
    Explanations

    lists of items or descriptions

    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
    èĮ¹
    -0.05
    oise
    -0.05
     objec
    -0.05
    ÑĥÑĩ
    -0.05
    umb
    -0.05
    éĤ£æł·
    -0.05
    ÙĦÙĪ
    -0.05
    ç²ĭ
    -0.05
    ÑģÑĤеÑģÑĤвенно
    -0.05
    allation
    -0.05
    POSITIVE LOGITS
    ayos
    0.06
    åĿĬ
    0.06
    èĤ¯
    0.06
    icitÃł
    0.06
    locals
    0.06
    hire
    0.06
    å·²ç»ıè¿ŀç»Ń
    0.06
    帮大家
    0.06
    pcs
    0.06
    ãĢģ“
    0.06
    Activations Density 0.028%

    No Known Activations