© 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. 6174
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    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
     tabs
    -0.25
    ä»ĬæĹ¥ãģ¯
    -0.25
    Īĺ
    -0.25
     Programmer
    -0.24
     WAN
    -0.24
    çe
    -0.24
    -hop
    -0.24
    Tabs
    -0.23
     frameborder
    -0.23
    iece
    -0.23
    POSITIVE LOGITS
    .pb
    0.27
    t
    0.26
    ãģĴ
    0.25
    ä¸Ģ段
    0.25
    åįģäºĶ
    0.24
    phase
    0.24
    _B
    0.24
     Flexible
    0.24
    åįģåħ«
    0.23
     subtle
    0.23
    Activations Density 0.058%

    No Known Activations