© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7050
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onth
    -0.26
     Deb
    -0.25
    ignal
    -0.25
    oltip
    -0.24
    æ¸ħæ¾Ī
    -0.24
    Ign
    -0.23
    ħ§
    -0.23
    å¾ĹåĪ°æľīæķĪ
    -0.23
    ocities
    -0.23
    æİĤ
    -0.23
    POSITIVE LOGITS
    çľĭä¸įè§ģ
    0.30
    auses
    0.28
     larg
    0.27
    æł¡
    0.27
    'aff
    0.26
    æĭĽçĶŁ
    0.25
    å¹ķåIJİ
    0.25
    ãĥªãĥ³
    0.24
     #__
    0.24
    ëŀĢ
    0.23
    Activations Density 0.460%

    No Known Activations

    This feature has no known activations.