© 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. 16944
    Prev
    Next
    INDEX
    Explanations

    Susan Schneider or Crown counsel

    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
    约è°Ī
    -0.05
    clam
    -0.05
    çĬĢ
    -0.05
    inari
    -0.05
    QUIS
    -0.05
    è¨Ģä¼ł
    -0.05
    zones
    -0.05
    çªģ
    -0.05
    esti
    -0.05
    æ¢ħæŀĹ
    -0.05
    POSITIVE LOGITS
    ä»İæĹł
    0.07
    dek
    0.06
    å±Ĭ
    0.05
    åģļçļĦæĺ¯
    0.05
    wear
    0.05
    mar
    0.05
    ultats
    0.05
    miss
    0.05
    åģļçļĦå°±æĺ¯
    0.05
     values
    0.05
    Activations Density 0.002%

    No Known Activations