© 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. 53309
    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
     mer
    -0.28
    jang
    -0.27
    æ³ķ令
    -0.26
     ki
    -0.26
    ERT
    -0.26
     ing
    -0.26
     Mer
    -0.25
     initial
    -0.25
     hit
    -0.25
    sert
    -0.24
    POSITIVE LOGITS
    panel
    0.28
     PANEL
    0.28
    baar
    0.28
    ocene
    0.27
     NOTICE
    0.27
    rase
    0.26
     mattered
    0.26
    æİ¥å¾ħ
    0.26
    herited
    0.26
    åĿĤ
    0.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.