© 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. 64468
    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
    ç»ĦåĽ¾
    -0.31
     пÑĢинÑı
    -0.31
    ä¸Ńåħ³
    -0.29
    dish
    -0.25
    ãĥĺãĥ«
    -0.24
     SHARES
    -0.23
     subsidi
    -0.23
    imeo
    -0.23
    GroupName
    -0.23
    ero
    -0.23
    POSITIVE LOGITS
    eed
    0.28
    Portrait
    0.26
    ç¼ĺ
    0.26
    åħ³ç³»
    0.26
    æĢİä¹Ī
    0.26
    ìĪł
    0.26
    åį°è±¡
    0.26
    åIJįä¹ī
    0.25
    çļĦè¯Ŀ
    0.25
    æŁı
    0.25
    Activations Density 3.278%

    No Known Activations

    This feature has no known activations.