© 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. 20-TRANSCODER-HP
    7. 130101
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perienced
    -0.26
    time
    -0.26
     trial
    -0.26
    è¿Ļ家ä¼Ļ
    -0.25
    åĬ¨çĶŁæĪIJ
    -0.25
    onus
    -0.24
     Narr
    -0.24
    à¸Ńร
    -0.24
     spontaneous
    -0.24
    ngrx
    -0.23
    POSITIVE LOGITS
    俱
    0.29
    举起
    0.29
    ä¸Ģä½ĵ
    0.27
     priorities
    0.26
    ican
    0.25
     FIG
    0.25
    èį¼
    0.25
    èľĥ
    0.25
     fall
    0.25
     graft
    0.24
    Activations Density 1.306%

    No Known Activations

    This feature has no known activations.