© 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. 4926
    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
    loff
    -0.28
    ç¡ĸ
    -0.26
     STDERR
    -0.26
     STILL
    -0.26
    judge
    -0.26
    æ»ļçIJĥ
    -0.25
    è§Ģå¯Ł
    -0.25
    ãĤ®ãĥ£
    -0.25
    棹
    -0.24
    ãĤ¢ãĤ¯ãĤ»ãĤ¹
    -0.24
    POSITIVE LOGITS
    plied
    0.28
     represented
    0.28
    麻
    0.27
    RM
    0.26
     vet
    0.26
    alth
    0.25
    é¾Ħ
    0.25
    ahoo
    0.24
    éħį
    0.24
    è£Ļ
    0.24
    Activations Density 0.099%

    No Known Activations

    This feature has no known activations.