© 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. 108030
    Prev
    Next
    INDEX
    Explanations

    nuclear

    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
    :Array
    -0.25
    .fileName
    -0.24
     bless
    -0.24
    èĩªæĦ¿
    -0.24
    :nil
    -0.24
     herself
    -0.24
     Ruf
    -0.24
    :<?
    -0.24
     Decompiled
    -0.24
     contributor
    -0.24
    POSITIVE LOGITS
     everything
    0.29
    i
    0.27
    Everything
    0.27
    åĹħ
    0.27
    ism
    0.27
    NE
    0.26
     role
    0.26
    NO
    0.26
    ä»Ģä¹Īéĥ½
    0.26
    ister
    0.25
    Activations Density 21.809%

    No Known Activations