© 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. 19-TRANSCODER-HP
    7. 8364
    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
    è¯Ĩ
    -0.25
    odel
    -0.25
    Inflater
    -0.25
     Assist
    -0.25
    åŁ¹
    -0.25
     distinct
    -0.24
    æĬĽå¼ĥ
    -0.23
    ãĤ°ãĥ«
    -0.23
    è¯ķ
    -0.23
    lations
    -0.23
    POSITIVE LOGITS
    monic
    0.29
     matchmaking
    0.26
     bunny
    0.25
    NavController
    0.25
     beforehand
    0.24
    byname
    0.24
     holland
    0.24
     Grove
    0.24
    æ´¥
    0.24
     FileAccess
    0.24
    Activations Density 0.033%

    No Known Activations

    This feature has no known activations.