© 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. 53341
    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
    IData
    -0.28
    妯
    -0.25
    หวาà¸Ļ
    -0.25
    anto
    -0.25
    æĸ§
    -0.24
    èĩĥ
    -0.24
    æ¡ĪåŃIJ
    -0.24
     Ranked
    -0.24
     Blacks
    -0.23
    골
    -0.23
    POSITIVE LOGITS
     diss
    0.25
    lesh
    0.25
    yd
    0.24
    itive
    0.24
    les
    0.24
     projection
    0.24
     Ferr
    0.24
     errorCallback
    0.24
    uilt
    0.23
    åįł
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.