© 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. 8513
    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
     boys
    -0.27
    .LENGTH
    -0.27
    åħħçĶµ
    -0.27
     points
    -0.25
     brave
    -0.25
    æĮĩåIJij
    -0.25
    çĶ·åŃ©
    -0.24
    çĮİ
    -0.24
     length
    -0.24
    èĭ¥
    -0.24
    POSITIVE LOGITS
    oque
    0.29
    WARE
    0.27
    mers
    0.26
    yw
    0.26
    é¤IJåħ·
    0.26
    FFECT
    0.26
    ISO
    0.25
    alte
    0.25
    ighb
    0.25
    semblies
    0.25
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.