© 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. 8809
    Prev
    Next
    INDEX
    Explanations

    cloud

    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
    âĢ¦”↵↵
    -0.34
    acements
    -0.29
    âĢ¦"↵↵
    -0.28
    âĢ¦”
    -0.27
    inition
    -0.27
     shim
    -0.27
    åľ°æ®µ
    -0.27
    peria
    -0.25
    âĢ¦.↵↵
    -0.24
    ,âĢ¦↵↵
    -0.24
    POSITIVE LOGITS
    CHE
    0.28
    ös
    0.24
    craft
    0.24
     Quick
    0.24
     quick
    0.24
    ãģĭ
    0.24
    -fast
    0.23
    Craft
    0.23
    season
    0.23
     harb
    0.23
    Activations Density 0.445%

    No Known Activations