© 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. 53696
    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
     set
    -0.44
    set
    -0.39
    åľ°æĸ¹
    -0.34
     Set
    -0.34
    设
    -0.34
    Set
    -0.33
    设å®ļ
    -0.32
    (set
    -0.32
     setId
    -0.31
    åľ°
    -0.31
    POSITIVE LOGITS
    æºĩ
    0.26
    isko
    0.26
    åı¼
    0.25
    quire
    0.25
    åĹ½
    0.25
    åIJIJ
    0.24
    并äºİ
    0.23
    æĪĸèĢħæĺ¯
    0.23
    =back
    0.23
    (Order
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.