© 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. 129947
    Prev
    Next
    INDEX
    Explanations

    Restrictions/legal documents

    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
    åıªæľī
    -0.35
     only
    -0.35
     practice
    -0.29
    åıªæľīä¸Ģ个
    -0.29
    åıªéľĢè¦ģ
    -0.28
    only
    -0.28
    åıªåī©ä¸ĭ
    -0.28
     mic
    -0.27
    ä¸Ģä¸Ģ
    -0.27
    å®ŀè·µ
    -0.26
    POSITIVE LOGITS
    ingers
    0.29
     veto
    0.26
     Eh
    0.26
     privileged
    0.25
    (Console
    0.25
    æľķ
    0.25
    .groupby
    0.25
    autoload
    0.24
    ªĮ
    0.23
    onitor
    0.23
    Activations Density 3.798%

    No Known Activations