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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7292
    Prev
    Next
    INDEX
    Explanations

    Positive reinforcement and correction

    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
    --*/↵
    -0.28
     fellows
    -0.27
    println
    -0.26
    ä¹ĭä¸Ģ
    -0.25
    ohl
    -0.25
    imit
    -0.25
    åį«
    -0.25
    管çIJĨç³»ç»Ł
    -0.25
    .dispatchEvent
    -0.24
    大åħ¨
    -0.24
    POSITIVE LOGITS
    å©´
    0.27
     Latest
    0.25
    æľĢæĸ°
    0.25
    icing
    0.25
    廿
    0.25
    fast
    0.24
    Air
    0.24
    èĤ±
    0.23
    dot
    0.23
    æ§Į
    0.23
    Activations Density 0.449%

    No Known Activations