© 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. 8115
    Prev
    Next
    INDEX
    Explanations

    Actions, events, occurrences

    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
     Centers
    -0.25
    roscope
    -0.25
    mers
    -0.25
    asca
    -0.25
    :right
    -0.24
     помоÑīÑĮ
    -0.24
     RIGHT
    -0.24
     centers
    -0.24
    /fr
    -0.24
    .Right
    -0.23
    POSITIVE LOGITS
    ä¹İ
    0.28
    æĿľåħ°
    0.27
    åįĵ
    0.26
    ä¸ļ
    0.26
    eful
    0.26
    ald
    0.26
    å®ŀè´¨
    0.25
    äºĭå®ŀä¸Ĭ
    0.25
    åħį
    0.25
    gain
    0.25
    Activations Density 0.641%

    No Known Activations