© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20293
    Prev
    Next
    INDEX
    Explanations

    is what / are what

    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
     A
    -0.07
    apon
    -0.06
     a
    -0.06
    icken
    -0.06
     D
    -0.05
    ä»ĵ
    -0.05
     L
    -0.05
    åħ³äºİåĬłå¼º
    -0.05
     an
    -0.05
    èįī
    -0.05
    POSITIVE LOGITS
    ownie
    0.07
    tul
    0.07
    enje
    0.06
    thead
    0.06
    sled
    0.06
    oops
    0.06
     bantu
    0.06
    íĺ¹
    0.06
    æīĢå±ķ示
    0.06
    iddy
    0.06
    Activations Density 0.003%

    No Known Activations