© 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. 130225
    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
     Laur
    -0.27
    OUNTER
    -0.27
    styl
    -0.25
    /Index
    -0.25
    çĶŁæ¶¯
    -0.25
    æĹħé¦Ĩ
    -0.24
     cig
    -0.24
    etypes
    -0.24
    berra
    -0.24
    edis
    -0.24
    POSITIVE LOGITS
    çĪĨåıij
    0.27
    rends
    0.25
    ripe
    0.25
    èĨº
    0.24
    æĶ¯æŁ±
    0.23
    $j
    0.23
     næ
    0.23
    åĬłå¤§å¯¹
    0.23
     echo
    0.23
    åįļè§Ī
    0.23
    Activations Density 0.918%

    No Known Activations

    This feature has no known activations.