© 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. 5157
    Prev
    Next
    INDEX
    Explanations

    Legal and database documents

    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
    èĬ½
    -0.27
    éªij
    -0.26
     tolerated
    -0.26
    Sink
    -0.26
    :S
    -0.25
    onymous
    -0.24
    oster
    -0.24
    人èĦī
    -0.24
    娩
    -0.23
    åı¤éķĩ
    -0.23
    POSITIVE LOGITS
    åħ¬åı¸ç«łç¨ĭ
    0.27
    ÑĭÑĪ
    0.26
    ott
    0.26
    ä¹Łéļıä¹ĭ
    0.26
    itar
    0.24
    è´¦
    0.24
    碰æĴŀ
    0.24
    VEL
    0.23
    Lit
    0.23
    [".
    0.23
    Activations Density 0.871%

    No Known Activations