© 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. 62895
    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
    广éĺĶçļĦ
    -0.28
    zza
    -0.27
    azi
    -0.26
     closed
    -0.25
     indoors
    -0.25
    稳å®ļæĢ§
    -0.25
    Move
    -0.24
     deployed
    -0.24
     done
    -0.24
    溢价
    -0.24
    POSITIVE LOGITS
    ä¹ł
    0.26
    assin
    0.24
    .vocab
    0.24
    iquer
    0.24
     thủy
    0.23
    ÑĤÑĢа
    0.23
    _buffers
    0.23
    ollar
    0.23
    ä½Ĩå®ĥ
    0.23
     affairs
    0.23
    Activations Density 4.041%

    No Known Activations

    This feature has no known activations.