© 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. 141462
    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
     societal
    -0.29
    åĶ±
    -0.28
    iem
    -0.26
    æĺ¾ç¤ºåĩº
    -0.26
    ¢åįķ
    -0.24
    åįģåŃĹ
    -0.24
    缴è¾ĸå¸Ĥ
    -0.24
    åĽ½å®¶æĪĺçķ¥
    -0.24
    çľģå¸Ĥ
    -0.23
    dm
    -0.23
    POSITIVE LOGITS
    istique
    0.26
    iore
    0.26
     vad
    0.25
    æĥ°
    0.25
    館
    0.25
     Rud
    0.25
    oment
    0.24
     urge
    0.24
     RU
    0.24
    ople
    0.24
    Activations Density 9.952%

    No Known Activations

    This feature has no known activations.