© 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. 142487
    Prev
    Next
    INDEX
    Explanations

    0

    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
    issing
    -0.27
    믹
    -0.24
     chars
    -0.24
    /rc
    -0.24
    -package
    -0.23
    ythe
    -0.23
     mê
    -0.23
    endra
    -0.23
    ÃŃc
    -0.23
     MyBase
    -0.22
    POSITIVE LOGITS
    åĩº
    0.25
     -->
    0.25
    塾
    0.25
    æ¼Ķç»İ
    0.24
    ugi
    0.24
     Epoch
    0.24
     ------>
    0.24
    碧
    0.24
    ç®Ģåįķ
    0.24
    lan
    0.23
    Activations Density 8.158%

    No Known Activations