© 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. 32-TRANSCODER-HP
    7. 42660
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    poke
    -0.30
    emens
    -0.28
    追éĹ®
    -0.26
    èıĬèĬ±
    -0.25
    orns
    -0.25
    æѦ
    -0.24
    åİ»çľĭ
    -0.24
     innocent
    -0.24
     sâu
    -0.24
     secret
    -0.24
    POSITIVE LOGITS
    çļĦåķĨåĵģ
    0.28
     Somerset
    0.27
    ocker
    0.25
    resse
    0.25
    Jer
    0.25
    parentNode
    0.25
    unce
    0.24
    没è§ģè¿ĩ
    0.24
     reports
    0.24
    ombine
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.