© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19658
    Prev
    Next
    INDEX
    Explanations

    seeking information or solutions

    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
    ä¸ĢçĶŁä¸Ń
    -0.06
    мок
    -0.06
     Spitzen
    -0.05
    临è¿ij
    -0.05
    erm
    -0.05
    uks
    -0.05
     riktigt
    -0.05
    attung
    -0.05
    zug
    -0.05
    å¨ĺåŃIJ
    -0.05
    POSITIVE LOGITS
    son
    0.06
    ith
    0.06
    ected
    0.05
     Barcl
    0.05
    ductor
    0.05
    nod
    0.05
    ector
    0.05
    antis
    0.05
     somehow
    0.05
     ÄijÃł
    0.05
    Activations Density 0.001%

    No Known Activations