© 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. 107217
    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
    praak
    -0.26
    ائÙĨ
    -0.26
    çĵł
    -0.26
    SSERT
    -0.25
    ç¿Ģ
    -0.25
     planta
    -0.24
     Pang
    -0.24
    ijke
    -0.23
    upiter
    -0.23
    -camera
    -0.23
    POSITIVE LOGITS
    no
    0.28
    IDA
    0.28
    не
    0.27
     no
    0.26
    Prof
    0.26
     Sick
    0.25
    享åıĹåĪ°
    0.25
    ç¥ĸ
    0.25
    çĥĪ
    0.25
    timeout
    0.25
    Activations Density 63.842%

    No Known Activations

    This feature has no known activations.