© 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. 8944
    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
     Elli
    -0.27
    jÄħ
    -0.26
    (Parse
    -0.25
    istik
    -0.24
    /language
    -0.24
    rame
    -0.24
    orro
    -0.24
    rng
    -0.24
    åıĹå½±åĵį
    -0.24
     quar
    -0.24
    POSITIVE LOGITS
    çī¹
    0.25
    лаÑĤ
    0.24
    Same
    0.23
     convenience
    0.23
    icot
    0.23
    .serialization
    0.23
     Bust
    0.23
     Poss
    0.23
    ŀæĢ§
    0.22
    urance
    0.22
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.