© 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. 141776
    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
    loo
    -0.30
     GMC
    -0.28
     fam
    -0.27
     family
    -0.26
    la
    -0.25
    gradable
    -0.25
    atic
    -0.25
     pres
    -0.25
    amen
    -0.25
    cla
    -0.25
    POSITIVE LOGITS
    ãĥĩãĤ£ãĥ³ãĤ°
    0.26
    çĴ
    0.26
     DEALINGS
    0.25
    çIJ°
    0.25
    çļĦ人æĿ¥è¯´
    0.25
    çݩ家æĿ¥è¯´
    0.25
    etail
    0.25
    éĺħ读åħ¨æĸĩ
    0.24
    ä¼ļ被
    0.24
    onis
    0.24
    Activations Density 15.129%

    No Known Activations

    This feature has no known activations.