© 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. 62983
    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
    æľīä¸įå°ij
    -0.27
    itor
    -0.27
    edo
    -0.26
     Generator
    -0.26
    lew
    -0.25
     ÑģоÑģÑĤоÑı
    -0.25
    fur
    -0.25
    Perform
    -0.25
    íħĶ
    -0.24
    ç»ĻæĤ¨
    -0.24
    POSITIVE LOGITS
    (stdin
    0.27
    éĶ²
    0.26
    丧
    0.26
     brigade
    0.26
     patron
    0.25
    translation
    0.25
     Patron
    0.25
     [/
    0.24
     translation
    0.24
    .AppendFormat
    0.24
    Activations Density 3.677%

    No Known Activations

    This feature has no known activations.