© 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. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142043
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹ¢åı¯ä»¥
    -0.26
    quel
    -0.25
    awks
    -0.25
    /feed
    -0.25
    åĽŀ家
    -0.24
    ä»»
    -0.24
    batim
    -0.24
    º«
    -0.23
    eth
    -0.23
     grown
    -0.23
    POSITIVE LOGITS
     Foam
    0.29
    ä¸Ģçķª
    0.26
    illusion
    0.26
    ulary
    0.26
    ünst
    0.25
    anse
    0.25
     fo
    0.25
     foam
    0.25
     Trudeau
    0.25
    íĴį
    0.25
    Activations Density 3.344%

    No Known Activations

    This feature has no known activations.