© 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. 63880
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
     ga
    -0.28
    åī²
    -0.27
     Zug
    -0.26
    çĶ¨åĬĽ
    -0.26
     tug
    -0.26
    é¹ĺ
    -0.26
     inc
    -0.26
    ect
    -0.25
    ä½ĵ
    -0.25
    åĬŁè¯¾
    -0.25
    POSITIVE LOGITS
    oftware
    0.27
    \"",
    0.26
    æĺī
    0.25
     ***/↵
    0.25
    çī¦
    0.24
     youngest
    0.24
    稳妥
    0.24
     hazır
    0.23
    \"",↵
    0.23
    "}}↵
    0.23
    Activations Density 51.194%

    No Known Activations