© 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. 141368
    Prev
    Next
    INDEX
    Explanations

    of

    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
    elon
    -0.28
    /apache
    -0.27
    ଡ
    -0.26
    zw
    -0.25
    achten
    -0.25
    leta
    -0.25
    ninger
    -0.25
    迹象
    -0.24
    ĺ认
    -0.24
    uft
    -0.23
    POSITIVE LOGITS
    atile
    0.28
    èģĶåIJĪ
    0.26
    Labour
    0.25
    ni
    0.24
    instancetype
    0.24
    VEL
    0.24
    åIJİæľŁ
    0.23
    ami
    0.23
    ued
    0.23
    Unhandled
    0.23
    Activations Density 22.193%

    No Known Activations