© 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. 54073
    Prev
    Next
    INDEX
    Explanations

    Articles

    np_max-act-logits · gemini-2.0-flash
    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
     Lö
    -0.25
    驾é©Ń
    -0.25
    ival
    -0.25
     amph
    -0.24
     market
    -0.24
    ellas
    -0.24
    å¾ħéģĩ
    -0.24
    ç½®
    -0.24
    ich
    -0.24
    èģĶ
    -0.24
    POSITIVE LOGITS
    åĬĽè¿ĺæĺ¯
    0.28
    assium
    0.26
    è¿ĺæĺ¯ä¼ļ
    0.25
    пÑĭ
    0.25
    eries
    0.25
     scand
    0.25
    aisy
    0.25
    kj
    0.25
    xmin
    0.25
    qui
    0.25
    Activations Density 0.008%

    No Known Activations