© 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. 63684
    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
    大æī¹
    -0.27
    uges
    -0.27
     VII
    -0.26
     Lives
    -0.25
     reciprocal
    -0.25
    è¾ĥ
    -0.25
     VI
    -0.25
     XVI
    -0.24
    æݧ
    -0.24
     TÃłi
    -0.23
    POSITIVE LOGITS
    ground
    0.32
    ä¹īä¹Į
    0.28
     lamb
    0.27
    issan
    0.27
     ground
    0.26
    çī¹æľĹ
    0.26
    iali
    0.25
    åIJįé¢Ŀ
    0.25
    {{$
    0.25
    ocode
    0.25
    Activations Density 3.890%

    No Known Activations

    This feature has no known activations.