© 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. 5190
    Prev
    Next
    INDEX
    Explanations

    Code/technical language

    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
    rates
    -0.30
    wright
    -0.27
     bn
    -0.26
    ragen
    -0.26
    bn
    -0.26
    rä
    -0.25
     ['./
    -0.25
    hart
    -0.25
    port
    -0.25
     Depos
    -0.25
    POSITIVE LOGITS
    .Skip
    0.26
    nage
    0.26
    nin
    0.25
    è¿Ļç§įäºĭæĥħ
    0.25
    èĩ³æѤ
    0.25
    æįĭ
    0.24
    NING
    0.24
    .jump
    0.24
    鸣
    0.24
    è¶Ĭ好
    0.24
    Activations Density 0.076%

    No Known Activations