© 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. 141110
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    vit
    -0.28
    ABA
    -0.26
    çݳ
    -0.26
    pla
    -0.25
    .fhir
    -0.25
    alta
    -0.24
    jax
    -0.24
     corner
    -0.24
    iver
    -0.24
    idal
    -0.24
    POSITIVE LOGITS
    ecc
    0.29
    çīºçī²
    0.26
    igans
    0.26
    åħ´
    0.26
    igung
    0.25
     szcz
    0.24
     fête
    0.24
     unins
    0.24
    developers
    0.24
    Send
    0.24
    Activations Density 31.280%

    No Known Activations