© 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. 20110
    Prev
    Next
    INDEX
    Explanations

    variable names and types

    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
     DataContext
    -0.06
    åį³åĪ»
    -0.06
    ذا
    -0.05
    embro
    -0.05
    oeuvre
    -0.05
    "
    -0.05
    loth
    -0.05
    çal
    -0.05
    holds
    -0.05
    rown
    -0.05
    POSITIVE LOGITS
    åį«çĶŁç»Ħç»ĩ
    0.06
    world
    0.05
    è¿Ľè¡Įä¸Ģ次
    0.05
    aad
    0.05
     ulang
    0.05
    åĩ«
    0.05
    æłĦ
    0.05
    shapes
    0.05
    æ¢Ĺ
    0.05
    庵
    0.05
    Activations Density 0.009%

    No Known Activations