© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4830
    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
     Chim
    -0.27
    HexString
    -0.25
    迷人
    -0.24
    plier
    -0.24
    ÑĮÑĤе
    -0.23
    åĪĨåŃIJ
    -0.23
     polic
    -0.22
     chem
    -0.22
    åĩĭ
    -0.22
     Amid
    -0.22
    POSITIVE LOGITS
    çģµæ´»æĢ§
    0.26
    refix
    0.26
    AndView
    0.25
     DEFINE
    0.24
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.24
    @show
    0.24
    å¤ļåľ°
    0.24
    并åıij
    0.23
     tou
    0.23
     verbal
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.