© 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. 6600
    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
    åıįä¹ĭ
    -0.27
     dép
    -0.26
    plat
    -0.26
    壳
    -0.26
    ãĥŀãĥ³ãĤ·ãĥ§ãĥ³
    -0.26
    ä¹ĭä¸Ń
    -0.24
    ä½ĵä¼ļ
    -0.24
    ilyn
    -0.24
     condo
    -0.24
     Âł
    -0.23
    POSITIVE LOGITS
    ç«¿
    0.27
    éĤ£ä½į
    0.25
    彩票
    0.25
    大åѸ
    0.24
    大åѦ
    0.24
     Bac
    0.24
    Mods
    0.24
    ircuit
    0.24
    太æŀģ
    0.23
    èĻ±
    0.23
    Activations Density 0.330%

    No Known Activations

    This feature has no known activations.