© 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. 63102
    Prev
    Next
    INDEX
    Explanations

    research papers with numbered parts

    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
    utor
    -0.26
    echa
    -0.26
    åij½ä¸Ń
    -0.25
    str
    -0.25
    åIJ¬è§ģ
    -0.24
    /lic
    -0.24
    orary
    -0.24
    ุม
    -0.24
    çĤ·
    -0.24
    çģ¶
    -0.24
    POSITIVE LOGITS
     wings
    0.27
    ignet
    0.26
    çļĦæĥħ
    0.25
    磾
    0.25
     stretches
    0.25
    æ´Ĺ
    0.24
    :UI
    0.23
     campaigned
    0.23
    çļĦå¿ĥæĢģ
    0.23
    Lng
    0.23
    Activations Density 4.868%

    No Known Activations