© 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. 5128
    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
    iente
    -0.28
    olie
    -0.26
    å¹Ĥ
    -0.26
    swer
    -0.26
    çļĦæľºä¼ļ
    -0.25
    Ref
    -0.25
    åĵij
    -0.25
    REF
    -0.25
    pcm
    -0.25
    è¢ĸ
    -0.25
    POSITIVE LOGITS
    isz
    0.27
    RID
    0.24
     Whether
    0.23
    phon
    0.23
    yps
    0.23
    åŃĺ
    0.23
    å®ĹæŨ
    0.23
     expectations
    0.23
    æĮģæľī
    0.23
    èģ
    0.23
    Activations Density 0.535%

    No Known Activations

    This feature has no known activations.