© 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. 17437
    Prev
    Next
    INDEX
    Explanations

    journaling, diary, reflection, lists

    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
    ç»Ļ对æĸ¹
    -0.08
    oner
    -0.07
    íĭĢ
    -0.07
    bery
    -0.07
     ourselves
    -0.07
    ONEY
    -0.06
    epend
    -0.06
    åĽ¢åĽ¢
    -0.06
    esas
    -0.06
    umpt
    -0.06
    POSITIVE LOGITS
    æĬļ
    0.05
    agi
    0.05
    idis
    0.05
    æĮ¨
    0.05
    æ·±èĵĿ
    0.05
    èĤ¤è´¨
    0.05
     pov
    0.05
     Kalender
    0.05
     downs
    0.05
     prose
    0.05
    Activations Density 0.004%

    No Known Activations