© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64557
    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
    eus
    -0.26
    apper
    -0.25
    /trunk
    -0.25
    èĭ¦
    -0.24
    bred
    -0.24
    åĪĨ解
    -0.24
    -yard
    -0.24
    åĨħåľ°
    -0.24
    reve
    -0.23
     assort
    -0.23
    POSITIVE LOGITS
    unts
    0.26
    quir
    0.26
    erti
    0.25
    ler
    0.25
    roat
    0.24
    ç®Ń
    0.24
     Trot
    0.24
    stands
    0.24
    abant
    0.24
    onomous
    0.23
    Activations Density 5.991%

    No Known Activations

    This feature has no known activations.