© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5085
    Prev
    Next
    INDEX
    Explanations

    up

    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
    tons
    -0.28
    lights
    -0.27
    rys
    -0.25
    ities
    -0.25
    ä¿İ
    -0.24
    åľ°å¸¦
    -0.24
    ritos
    -0.23
     Rays
    -0.23
    主ä¹īèĢħ
    -0.23
    _mappings
    -0.23
    POSITIVE LOGITS
    /layout
    0.23
    ulin
    0.23
    /down
    0.22
    ../../../
    0.21
    plements
    0.21
    åĴĮæĶ¯æĮģ
    0.21
    /find
    0.21
    cri
    0.21
    ALLOC
    0.21
     Freed
    0.21
    Activations Density 0.838%

    No Known Activations