© 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. 7773
    Prev
    Next
    INDEX
    Explanations

    code/licensing

    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
    Ya
    -0.25
    isty
    -0.24
    è°¯
    -0.24
    ican
    -0.23
    ocker
    -0.23
    EK
    -0.22
     hé
    -0.22
     Sims
    -0.22
     therefore
    -0.22
    Dou
    -0.22
    POSITIVE LOGITS
    uality
    0.23
    è¿Ļåıªæĺ¯
    0.23
    uels
    0.23
    á¹ĩ
    0.23
     vá»ĩ
    0.23
    åħ·ä½ĵçļĦ
    0.22
    uale
    0.22
    uja
    0.21
    解æĶ¾æĢĿæĥ³
    0.21
    干货
    0.21
    Activations Density 0.042%

    No Known Activations