© 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. 129490
    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
    ä¿Ŀåį«
    -0.27
    ARRIER
    -0.25
     Hip
    -0.25
    ä¸įæľį
    -0.25
    xda
    -0.25
     carry
    -0.25
     conspic
    -0.25
     ordin
    -0.25
    缮çļĦ
    -0.25
    rale
    -0.24
    POSITIVE LOGITS
    éĤ£ä¹Ī
    0.29
    usch
    0.28
    缸å½ĵäºİ
    0.26
    æ·»åĬłåīĤ
    0.25
     Affero
    0.25
    olated
    0.24
    GetInt
    0.24
     Euras
    0.24
    èĩ³ä¸Ĭ
    0.24
    -Identifier
    0.23
    Activations Density 3.015%

    No Known Activations

    This feature has no known activations.