© 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. 53342
    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
    åĮª
    -0.28
    thic
    -0.28
    view
    -0.26
    ç¼ľ
    -0.26
    (nr
    -0.25
     deduct
    -0.24
     blitz
    -0.24
     Fo
    -0.24
     tslib
    -0.24
    æį»
    -0.24
    POSITIVE LOGITS
    ики
    0.29
    åĨ°
    0.28
    inke
    0.27
     açıl
    0.26
     Preparation
    0.26
    磶
    0.25
     preparations
    0.25
     preparation
    0.25
    è£ħ
    0.24
    ç¡Į
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.