© 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. 20733
    Prev
    Next
    INDEX
    Explanations

    city names, competitions, and people

    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
    atina
    -0.06
    以æ¡Ī
    -0.05
    cmc
    -0.05
     perce
    -0.05
     resolving
    -0.05
    ืà¹īà¸Ńà¸ĩ
    -0.05
    Oc
    -0.05
    ayah
    -0.05
    ühlen
    -0.05
     иÑģполнение
    -0.05
    POSITIVE LOGITS
     tempér
    0.06
     Shiite
    0.05
     hứng
    0.05
    pear
    0.05
    -cigarettes
    0.05
    ç¬ĶçĶ»
    0.05
    peg
    0.05
    βα
    0.05
    tem
    0.05
    gni
    0.05
    Activations Density 0.001%

    No Known Activations