© 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. 64083
    Prev
    Next
    INDEX
    Explanations

    person

    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
    å¯Ĩ
    -0.28
    è´¨
    -0.25
     yourselves
    -0.25
    erved
    -0.24
    adora
    -0.24
    as
    -0.24
    ibern
    -0.23
    ating
    -0.23
     certainly
    -0.23
    registry
    -0.23
    POSITIVE LOGITS
    对åѦçĶŁ
    0.27
    tone
    0.26
    .hs
    0.26
    wise
    0.25
    .subplots
    0.25
     torn
    0.25
     chained
    0.25
     interpolated
    0.25
    unik
    0.25
    rition
    0.25
    Activations Density 9.864%

    No Known Activations