© 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. 33-TRANSCODER-HP
    7. 54344
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urable
    -0.30
    stüt
    -0.28
    ynchronously
    -0.28
    tees
    -0.26
    prus
    -0.26
    edImage
    -0.26
    addtogroup
    -0.25
    ibile
    -0.25
    une
    -0.25
    aic
    -0.25
    POSITIVE LOGITS
    æİ·
    0.28
     inc
    0.27
    æĵį
    0.26
    å®ĭ
    0.25
     often
    0.25
     минÑĥÑĤ
    0.24
     redraw
    0.24
    OUNTER
    0.23
    ä¸īæĸ¹
    0.23
    isia
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.