© 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. 108506
    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
    agal
    -0.28
    illions
    -0.25
    agas
    -0.25
    æķ²
    -0.25
    ä»ĸ们çļĦ
    -0.24
    .AutoComplete
    -0.24
    åĮĹæŀģ
    -0.24
    parity
    -0.24
    Based
    -0.24
    绢
    -0.24
    POSITIVE LOGITS
     clinically
    0.26
     mercy
    0.25
    ä»İæł¹æľ¬ä¸Ĭ
    0.25
    izr
    0.24
    lates
    0.24
    greso
    0.24
    estone
    0.24
     админиÑģÑĤÑĢа
    0.23
     Twe
    0.23
    angep
    0.23
    Activations Density 2.584%

    No Known Activations

    This feature has no known activations.