© 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. 107468
    Prev
    Next
    INDEX
    Explanations

    health

    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
    Ahead
    -0.26
    -mount
    -0.26
     mount
    -0.25
     HS
    -0.25
    SION
    -0.25
    .design
    -0.25
    /target
    -0.24
    *dt
    -0.23
    OMETRY
    -0.23
     Lamb
    -0.23
    POSITIVE LOGITS
    -exc
    0.30
    cbc
    0.28
     unjust
    0.28
    cola
    0.26
    auses
    0.26
    -Pack
    0.26
     misses
    0.24
    æŃ£å½ĵ
    0.24
    recv
    0.24
    apas
    0.24
    Activations Density 7.305%

    No Known Activations