© 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. 5959
    Prev
    Next
    INDEX
    Explanations

    Media- or biography-related articles

    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
    åij
    -0.32
    tör
    -0.28
    kers
    -0.28
    bel
    -0.27
    å°Ķæĸ¯
    -0.26
    ä¸Ńå°ıåŀĭ
    -0.26
    çű
    -0.26
    osite
    -0.26
    第ä¸ĢæĿ¡
    -0.26
    ioms
    -0.26
    POSITIVE LOGITS
    对æĬĹ
    0.31
    翼
    0.28
    ich
    0.25
    Arch
    0.24
     Barn
    0.24
     ÑģпоÑģоб
    0.24
    <r
    0.23
     Build
    0.23
     indu
    0.23
    éĺ´
    0.23
    Activations Density 0.149%

    No Known Activations