© 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. 18402
    Prev
    Next
    INDEX
    Explanations

    complete this form / complete the game / what comes next

    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
    ç¼ķ
    -0.06
     bit
    -0.06
    ward
    -0.06
    лей
    -0.05
     Ho
    -0.05
     under
    -0.05
    anco
    -0.05
    most
    -0.05
    æĭĤ
    -0.05
    pus
    -0.05
    POSITIVE LOGITS
    缴ãģĹ
    0.06
    ีà¹Īย
    0.06
    éĢłè¡Ģ
    0.06
     rightly
    0.05
    è¡¥ç»Ļ
    0.05
    åIJĮå·¥
    0.05
    æij
    0.05
    rero
    0.05
    igli
    0.05
    .assertNull
    0.05
    Activations Density 0.002%

    No Known Activations