© 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. 129967
    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
    å¹³åı°ä¸Ĭ
    -0.28
    Sab
    -0.27
    OLDER
    -0.26
     Bootstrap
    -0.25
    è¯įæĿ¡
    -0.24
    anch
    -0.24
    æĥħ人
    -0.23
    _Frame
    -0.23
     Caval
    -0.23
    åł´
    -0.23
    POSITIVE LOGITS
    nts
    0.28
    idos
    0.27
    portun
    0.27
    imu
    0.25
    ettes
    0.24
    bytes
    0.24
     whereabouts
    0.23
    posables
    0.23
    ewhere
    0.23
    解åĨ³éĹ®é¢ĺ
    0.23
    Activations Density 33.953%

    No Known Activations

    This feature has no known activations.