© 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. 57685
    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
    åħį
    -0.30
     darm
    -0.28
    >window
    -0.25
    æ£ł
    -0.25
    æĹ»
    -0.24
    Declare
    -0.24
    ç«£
    -0.24
     drill
    -0.24
    married
    -0.23
    gue
    -0.23
    POSITIVE LOGITS
    ards
    0.26
    |)↵
    0.25
    综
    0.24
    abbo
    0.24
    cred
    0.24
    oref
    0.24
    èµ°è¿ij
    0.24
    |,↵
    0.23
    rsa
    0.23
    说æľį
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.