© 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. 107579
    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
     rej
    -0.25
    mitters
    -0.25
    ainty
    -0.23
     GTA
    -0.23
    BCM
    -0.22
    chalk
    -0.22
    olid
    -0.22
    itution
    -0.22
    mpz
    -0.22
    hos
    -0.21
    POSITIVE LOGITS
     oct
    0.25
     known
    0.25
    éļħ
    0.25
    æ¥ŀ
    0.24
    è·¨
    0.24
    bio
    0.24
    modules
    0.24
     compte
    0.24
    gle
    0.23
    å½¼
    0.23
    Activations Density 22.912%

    No Known Activations

    This feature has no known activations.