Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 27-TRANSCODER-HP
    4. 1099
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľĢ大éĻIJ度
    -0.27
    pray
    -0.24
    çļĦé«ĺ度
    -0.24
    phant
    -0.23
    aney
    -0.23
     Unidos
    -0.23
     Panc
    -0.23
    大å®Ĺ
    -0.23
     lineWidth
    -0.23
    InOut
    -0.23
    POSITIVE LOGITS
    ç®Ģ
    0.32
     Moments
    0.31
    ç°¡
    0.27
    {/
    0.27
     moments
    0.27
    ught
    0.25
     inspections
    0.25
    ikt
    0.25
    bers
    0.24
     simplify
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.