© 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. 54054
    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
    ếc
    -0.26
     disruptive
    -0.26
     conv
    -0.25
    è¾ħ
    -0.25
     нек
    -0.24
     mo
    -0.24
    èĨĤ
    -0.24
     sweep
    -0.24
    FileVersion
    -0.24
    ä½ľæĸĩ
    -0.24
    POSITIVE LOGITS
    etter
    0.27
    æĹ´
    0.26
    LOS
    0.26
     Plans
    0.25
    fare
    0.25
    åºIJ
    0.25
    çĶ³æĬ¥
    0.25
    geme
    0.24
    Bel
    0.24
    认è¯Ĩ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.