© 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. 19016
    Prev
    Next
    INDEX
    Explanations

    film opens with

    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
    -0.06
    éģĵ
    -0.06
    mand
    -0.05
    -
    -0.05
     f
    -0.05
     un
    -0.05
    ↵↵
    -0.05
    -0.05
     Un
    -0.05
    ,
    -0.05
    POSITIVE LOGITS
    erne
    0.07
    enzo
    0.07
    åĽī
    0.07
    erstellung
    0.07
    umpang
    0.07
     tutv
    0.07
    è¿ĺç»Ļ
    0.07
    emel
    0.07
    vais
    0.07
    æľī空
    0.07
    Activations Density 0.021%

    No Known Activations