© 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. 32-TRANSCODER-HP
    7. 41463
    Prev
    Next
    INDEX
    Explanations

    Text from published works

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abor
    -0.28
    haven
    -0.27
    .rs
    -0.27
     cub
    -0.24
     abb
    -0.24
    ç«Ļåľ¨
    -0.24
    箩
    -0.24
     workers
    -0.24
    .worker
    -0.24
    progressbar
    -0.23
    POSITIVE LOGITS
     Latina
    0.28
    egra
    0.26
     Chapman
    0.26
    id
    0.25
    sy
    0.25
    èIJ¤
    0.25
    ogi
    0.25
     ~(
    0.24
    .Utility
    0.24
    人家
    0.24
    Activations Density 0.002%

    No Known Activations