© 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. 140972
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
    ä¿IJ
    -0.27
    uC
    -0.25
    .getP
    -0.24
    åĢŁæѤ
    -0.24
    ç²²
    -0.24
    æħĪ
    -0.23
    çĶ±æѤ
    -0.23
    fortune
    -0.23
    zeros
    -0.23
     Freeze
    -0.23
    POSITIVE LOGITS
    奥æŀĹåĮ¹åħĭ
    0.30
    ä¸Ģå¾ĭ
    0.29
    äºĽä»Ģä¹Ī
    0.29
    agi
    0.28
    车
    0.26
    çĺ¾
    0.26
    ikal
    0.25
    variably
    0.25
    æĪijçĪ±ä½ł
    0.24
    å¤ļä¹ħ
    0.24
    Activations Density 47.674%

    No Known Activations