© 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. 142071
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    roups
    -0.26
    åĩŃè¯ģ
    -0.26
    csr
    -0.25
    éĴĪ对
    -0.24
     Lau
    -0.24
    ẩ
    -0.24
    å¢Ļ
    -0.24
     repro
    -0.23
    jos
    -0.23
    .ga
    -0.23
    POSITIVE LOGITS
    å¾®è§Ĥ
    0.31
    INF
    0.27
     pron
    0.27
    缤
    0.26
    èĿ
    0.25
    çĽĺ
    0.25
    并éĢļè¿ĩ
    0.25
     replacement
    0.25
     disks
    0.24
    é¸
    0.23
    Activations Density 3.537%

    No Known Activations

    This feature has no known activations.