© 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. 17733
    Prev
    Next
    INDEX
    Explanations

    community and service

    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
    otropic
    -0.07
    otrop
    -0.06
    ListNode
    -0.06
    ationally
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    CLU
    -0.06
    迷人
    -0.06
    åħ¨èº«çļĦ
    -0.06
    iky
    -0.06
    TreeNode
    -0.06
    POSITIVE LOGITS
     ал
    0.06
    venience
    0.05
     famili
    0.05
    æĿŁ
    0.05
    æīĴ
    0.05
     al
    0.05
    诣
    0.05
    æģ³
    0.05
    鼷
    0.05
    è½°
    0.05
    Activations Density 0.010%

    No Known Activations