© 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. 64346
    Prev
    Next
    INDEX
    Explanations

    Code/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
    anko
    -0.31
    Morning
    -0.29
    emics
    -0.27
     Supports
    -0.26
    åĭŁ
    -0.25
    ewe
    -0.25
    çŀĢ
    -0.24
     Leaves
    -0.24
     comrades
    -0.24
    æĶ¯æı´
    -0.24
    POSITIVE LOGITS
    TypeId
    0.27
     saf
    0.26
    帮æĪij
    0.25
    对æĪij
    0.25
    оÑĢÑĤ
    0.24
    .zero
    0.24
    çĽ
    0.24
    ç½Ĥ
    0.24
    TypeName
    0.24
    è¶Ĭè¿ĩ
    0.24
    Activations Density 0.547%

    No Known Activations