© 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. 53693
    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
    æĺŁçº§
    -0.30
    osit
    -0.28
     oui
    -0.26
     Fres
    -0.26
    _bullet
    -0.25
    otron
    -0.25
    èµĶ
    -0.24
    åģ¿
    -0.24
    æ°¨éħ¸
    -0.24
    ä¸Ģ页
    -0.23
    POSITIVE LOGITS
    antz
    0.25
    antis
    0.24
    ALES
    0.24
    ale
    0.24
    vr
    0.24
    itime
    0.24
    ç´«
    0.24
    ±Ð¾ÑĤ
    0.24
     figure
    0.23
     ((!
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.