© 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. 8075
    Prev
    Next
    INDEX
    Explanations

    Excerpts

    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
     even
    -0.31
    gree
    -0.29
     so
    -0.29
    ä¸ĩåħĥ以ä¸Ĭ
    -0.28
    èħĬ
    -0.28
     related
    -0.28
    ipse
    -0.27
    matic
    -0.27
     form
    -0.26
     beard
    -0.25
    POSITIVE LOGITS
    åħ¨èĩªåĬ¨
    0.25
    izin
    0.25
     nodeList
    0.25
    иÑģк
    0.25
     MyBase
    0.25
    çIJĨæĥ³çļĦ
    0.24
     Fry
    0.24
    ISA
    0.24
    /Edit
    0.24
    çļĦåѦçĶŁ
    0.24
    Activations Density 0.025%

    No Known Activations