© 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. 31-TRANSCODER-HP
    7. 19212
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gc
    -0.39
     gc
    -0.38
    _rc
    -0.37
    RC
    -0.36
    _gc
    -0.35
     GC
    -0.35
    (gc
    -0.35
     rc
    -0.35
    dc
    -0.34
    DC
    -0.32
    POSITIVE LOGITS
    ceb
    0.26
    avia
    0.26
    {return
    0.26
    ffe
    0.26
     onto
    0.24
     MSR
    0.24
     аб
    0.24
    饷
    0.24
     abdomen
    0.24
    oton
    0.24
    Activations Density 2.543%

    No Known Activations