© 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. 62976
    Prev
    Next
    INDEX
    Explanations

    academic/technical discussions

    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
    quila
    -0.29
    idency
    -0.29
    inces
    -0.27
    ä¸ªé¡¹çĽ®
    -0.27
    opal
    -0.25
    对该
    -0.25
    Tro
    -0.25
    .plus
    -0.25
    ifter
    -0.25
    urgeon
    -0.24
    POSITIVE LOGITS
    åĵ²åѦ
    0.27
    abr
    0.26
    polate
    0.25
    rÃŃ
    0.25
    brates
    0.24
     sentido
    0.24
    pan
    0.24
     componentDid
    0.24
    缴åįĩ
    0.23
     philosopher
    0.23
    Activations Density 33.496%

    No Known Activations