© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142398
    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
    çIJ¥
    -0.31
    é¢ĦçķĻ
    -0.29
    dest
    -0.26
    å¹²
    -0.26
    ustr
    -0.25
    çķĻ
    -0.25
    phone
    -0.24
    è¶Ĭå¤ļ
    -0.24
    incr
    -0.24
    arming
    -0.24
    POSITIVE LOGITS
     geh
    0.31
     Ãĸnceki
    0.25
    éĺ²å¾¡
    0.24
     Packs
    0.24
    umber
    0.24
    å¦Ī
    0.23
     consciousness
    0.23
    Def
    0.23
    udos
    0.23
     SEARCH
    0.23
    Activations Density 38.082%

    No Known Activations

    This feature has no known activations.