© 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. 142032
    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
    cosystem
    -0.28
    ACHE
    -0.27
    èį·
    -0.27
     effects
    -0.26
     Effects
    -0.25
    ÑĤÑĢаÑĤ
    -0.24
    validators
    -0.24
    æĪij个人
    -0.24
    åħĥ件
    -0.23
    强奸
    -0.23
    POSITIVE LOGITS
     rings
    0.28
     amort
    0.27
    ãģĤãĤĬãģĮãģ¨ãģĨ
    0.25
     scrolled
    0.25
    åľ¨ä¸Ĭæµ·
    0.24
    ellant
    0.24
    hazi
    0.24
     peg
    0.24
     Harbour
    0.24
    graf
    0.24
    Activations Density 7.017%

    No Known Activations

    This feature has no known activations.