© 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. 141609
    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
     dice
    -0.26
    ARAM
    -0.26
    驺
    -0.26
    å¹£
    -0.25
    笺
    -0.25
     coin
    -0.24
    Dice
    -0.24
    廣åijĬ
    -0.24
    楼ä¸ĭ
    -0.23
    æ§Ľ
    -0.23
    POSITIVE LOGITS
    åĪĹ车
    0.26
    udes
    0.26
    comes
    0.25
    itel
    0.25
    ESIS
    0.24
     OWN
    0.24
    ellan
    0.24
    umo
    0.24
    车主
    0.23
    rees
    0.23
    Activations Density 0.605%

    No Known Activations

    This feature has no known activations.