© 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. 129954
    Prev
    Next
    INDEX
    Explanations

    Technical/academic texts

    np_max-act · gemini-2.0-flash
    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
    潦
    -0.28
     caught
    -0.25
    RESULT
    -0.24
    Plus
    -0.24
    èĭ´
    -0.24
    plus
    -0.24
     polÃŃt
    -0.24
     entered
    -0.23
    éļ¶
    -0.23
     losers
    -0.23
    POSITIVE LOGITS
    istem
    0.28
    teenth
    0.26
     bakım
    0.25
     hazırlan
    0.24
     American
    0.24
     touch
    0.24
    峤
    0.23
    atto
    0.23
    ouston
    0.23
    宸
    0.23
    Activations Density 8.187%

    No Known Activations