© 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. 18845
    Prev
    Next
    INDEX
    Explanations

    Related content markers

    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
     Noti
    -0.07
    elm
    -0.06
    åįİåºŃ
    -0.06
    swith
    -0.06
    oter
    -0.06
    wijk
    -0.06
    å¸ĥæĸ¯
    -0.06
    orners
    -0.06
    tees
    -0.06
    ronics
    -0.06
    POSITIVE LOGITS
    认
    0.05
    iedo
    0.05
     nou
    0.05
    ueil
    0.05
    对å®ĥ
    0.05
    çĬ¹
    0.05
     г
    0.04
    ehren
    0.04
     kö
    0.04
    çĬ
    0.04
    Activations Density 0.019%

    No Known Activations