© 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. 53909
    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
    å·³
    -0.31
     stretch
    -0.28
    .deep
    -0.27
    æį©
    -0.27
     stretched
    -0.26
     &,
    -0.26
    éģĹä¼ł
    -0.25
     quanto
    -0.25
     stretches
    -0.25
     Yourself
    -0.24
    POSITIVE LOGITS
    èĬ±èįī
    0.28
    ä¸İåħ¶
    0.28
    ho
    0.27
    ãĤ¹ãĥĨ
    0.27
    äºĭ
    0.27
    hoa
    0.25
    项
    0.24
    /rfc
    0.24
     def
    0.24
    etrofit
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.