© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19940
    Prev
    Next
    INDEX
    Explanations

    `.where` filtering and conditional logic

    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
     toll
    -0.05
    ç¶
    -0.05
     aff
    -0.05
     Toll
    -0.04
    NAL
    -0.04
     au
    -0.04
    (
    -0.04
    Âł
    -0.04
    å¼
    -0.04
    -0.04
    POSITIVE LOGITS
    âĢ¦]
    0.07
    lesai
    0.07
    cedes
    0.07
    å·¥ç¨ĭç³»
    0.07
     consigo
    0.06
    ısınız
    0.06
    å¿«çľĭ
    0.06
     *}
    0.06
    aurus
    0.06
    quiera
    0.06
    Activations Density 0.013%

    No Known Activations