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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5422
    Prev
    Next
    INDEX
    Explanations

    Mixed articles and captions

    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
    åĽ¾ä¸º
    -0.49
    åĽ¾
    -0.43
     åĽ¾
    -0.39
    Figure
    -0.38
    示
    -0.38
    åIJĪå½±
    -0.36
    FIG
    -0.36
     FIG
    -0.34
     Figure
    -0.33
    .jpg
    -0.32
    POSITIVE LOGITS
    çĩİ
    0.29
    enberg
    0.27
    оÑĦ
    0.26
    èİ´
    0.24
     Canton
    0.24
    iedades
    0.24
    istle
    0.24
    åĽ°æĥij
    0.23
    RI
    0.23
     synonym
    0.23
    Activations Density 0.003%

    No Known Activations