© 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. 57641
    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
    agus
    -0.30
    aji
    -0.27
    ño
    -0.26
    -trained
    -0.26
     trained
    -0.25
    oken
    -0.24
     whatsoever
    -0.24
     ;č↵č↵
    -0.24
    >>&
    -0.24
     Shooter
    -0.23
    POSITIVE LOGITS
    iro
    0.27
    iselect
    0.24
    utar
    0.24
    ecer
    0.23
    eh
    0.23
    ptions
    0.23
    ohn
    0.23
    ader
    0.23
    ilm
    0.23
    iras
    0.23
    Activations Density 0.889%

    No Known Activations

    This feature has no known activations.