© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7940
    Prev
    Next
    INDEX
    Explanations

    URLs, dates, emails, code

    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
    pheric
    -0.26
    éħ¿
    -0.25
    sic
    -0.25
    pcf
    -0.24
     theirs
    -0.24
    çļĦåİĭåĬĽ
    -0.24
     globalization
    -0.24
    sla
    -0.24
    ammo
    -0.23
    ặ
    -0.23
    POSITIVE LOGITS
    æĺ¯æľĢ
    0.27
    许
    0.24
     QMainWindow
    0.23
    åħijçİ°
    0.23
    ink
    0.23
    chaft
    0.23
    ittest
    0.23
    ãģĭãģ¤
    0.23
    клад
    0.23
    curr
    0.23
    Activations Density 0.006%

    No Known Activations