© 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. 108468
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    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
    olis
    -0.30
    ingers
    -0.26
    -vs
    -0.26
    lob
    -0.25
    rud
    -0.25
    èĢ³
    -0.25
    èĤĥ
    -0.24
    说æĺİ
    -0.24
    éĤ£åĦ¿
    -0.23
    纸ä¸Ĭ
    -0.23
    POSITIVE LOGITS
     lineage
    0.26
     packed
    0.26
    /question
    0.25
     Pant
    0.25
    ioned
    0.25
    åĽŀèIJ½
    0.24
    .unpack
    0.24
     packing
    0.24
    åį
    0.24
     consultation
    0.23
    Activations Density 12.765%

    No Known Activations