© 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. 19-TRANSCODER-HP
    7. 8824
    Prev
    Next
    INDEX
    Explanations

    superlatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fully
    -0.28
     xxx
    -0.28
    legal
    -0.27
    ovel
    -0.27
     ingredient
    -0.26
     full
    -0.26
    enef
    -0.26
     identical
    -0.25
     Fully
    -0.25
    çİĦ
    -0.25
    POSITIVE LOGITS
    swer
    0.30
    ä½Ī
    0.27
     conting
    0.27
     dips
    0.27
    iling
    0.27
    ä¸įæĸ·
    0.26
    acus
    0.26
    elize
    0.25
    alley
    0.25
    麽
    0.25
    Activations Density 0.002%

    No Known Activations