© 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. 7604
    Prev
    Next
    INDEX
    Explanations

    Venus

    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
    ein
    -0.30
     rozwiÄħz
    -0.24
    -routing
    -0.24
    indy
    -0.23
    akes
    -0.23
    ụ
    -0.23
    yle
    -0.22
    ailing
    -0.22
    chain
    -0.22
    á»Ļng
    -0.22
    POSITIVE LOGITS
     Sized
    0.33
    esian
    0.26
    bine
    0.26
    kil
    0.26
    ian
    0.25
    çľĭä¸Ģçľĭ
    0.24
     appropriately
    0.24
    ä¹Łä¸įåı¯èĥ½
    0.23
    é¦ĸåħĪæĺ¯
    0.23
     cert
    0.23
    Activations Density 0.275%

    No Known Activations