© 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. 27-TRANSCODER-HP
    7. 56870
    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
    outil
    -0.30
    è¯Ĺ
    -0.27
     killing
    -0.27
    zik
    -0.25
     getFile
    -0.24
    çĸ´
    -0.24
    åħĨ
    -0.24
    rif
    -0.24
    å°Ĩ以
    -0.24
    angler
    -0.24
    POSITIVE LOGITS
    ords
    0.28
     Corner
    0.27
    ars
    0.25
     rá»Ļng
    0.24
    Usage
    0.24
    phans
    0.24
    æĦŁäºº
    0.23
    elocity
    0.23
    anship
    0.23
    æĿĤ
    0.23
    Activations Density 0.199%

    No Known Activations

    This feature has no known activations.