© 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. 130640
    Prev
    Next
    INDEX
    Explanations

    technical language and code

    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
    æĭIJ
    -0.26
    omite
    -0.25
    okie
    -0.25
     Leia
    -0.24
    arse
    -0.24
    é»Ħçĵľ
    -0.24
    æĮĩåIJij
    -0.24
     swings
    -0.23
    åĽºå®ļçļĦ
    -0.23
    CAM
    -0.23
    POSITIVE LOGITS
    .preference
    0.27
     Gross
    0.27
    roy
    0.26
     borrow
    0.26
    åĢŁ
    0.25
    зоÑĢ
    0.25
    çĩĥæ°Ķ
    0.24
     prest
    0.24
     warn
    0.24
    боÑĢ
    0.24
    Activations Density 26.938%

    No Known Activations