© 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. 20863
    Prev
    Next
    INDEX
    Explanations

    list formatting

    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
    idd
    -0.06
    å°¸
    -0.06
    orgen
    -0.05
    owie
    -0.05
    UTION
    -0.05
    elé
    -0.05
    åħľ
    -0.05
    ä¸Ńè¡Į
    -0.05
     Identity
    -0.05
    rown
    -0.05
    POSITIVE LOGITS
    å·²ç»ıæĪIJ为äºĨ
    0.06
    udes
    0.06
    mind
    0.06
    çľ·
    0.06
     fl
    0.05
    å°¤åħ¶æĺ¯åľ¨
    0.05
     viag
    0.05
    并ä¸į大
    0.05
    ä¸įå¼Ģ
    0.05
    ëį°ìļĶ
    0.05
    Activations Density 0.024%

    No Known Activations