© 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. 141915
    Prev
    Next
    INDEX
    Explanations

    Code special characters

    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
     Printf
    -0.28
    åĬŀ好
    -0.25
    sprintf
    -0.24
    ï¬Ĥ
    -0.24
     życ
    -0.24
    weathermap
    -0.24
     ï
    -0.24
    å¿«
    -0.23
     Countdown
    -0.23
    .mozilla
    -0.23
    POSITIVE LOGITS
    ONO
    0.31
    eping
    0.29
    çĪ±ç¾İ
    0.28
     lov
    0.28
    alon
    0.27
    eker
    0.27
    amon
    0.27
    iname
    0.26
    epam
    0.26
    ective
    0.26
    Activations Density 7.232%

    No Known Activations