© 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. 17916
    Prev
    Next
    INDEX
    Explanations

    importance or possibility

    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
    sons
    -0.06
    ,
    -0.06
    اث
    -0.05
    -0.05
    aston
    -0.05
    .
    -0.05
     /
    -0.05
    ова
    -0.05
    ente
    -0.05
     xxx
    -0.05
    POSITIVE LOGITS
    èĩªå·±
    0.08
    æľīèĩ´
    0.08
    quoi
    0.08
    æīĵäºĨ个
    0.07
    ä¸ĥæĪIJ
    0.07
    äºĨè¿ij
    0.07
    ëĸ»
    0.07
    Ù°
    0.07
    weise
    0.07
    you
    0.06
    Activations Density 0.002%

    No Known Activations