© 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. 41555
    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
     starting
    -0.32
     Starting
    -0.30
     first
    -0.28
    iliar
    -0.28
     th
    -0.27
    (t
    -0.27
    ↵↵
    -0.26
    (first
    -0.26
    ingu
    -0.26
    第ä¸Ģ个
    -0.26
    POSITIVE LOGITS
    ä½Ĩæĺ¯å¦Ĥæŀľ
    0.27
    端æŃ£
    0.27
    tent
    0.27
    AW
    0.27
    รา
    0.26
     Dustin
    0.26
    就说
    0.26
    acad
    0.26
     way
    0.26
    ustr
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.