© 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. 6911
    Prev
    Next
    INDEX
    Explanations

    IEEE

    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
    çħ¨
    -0.25
    ttp
    -0.25
    ead
    -0.25
    JM
    -0.25
    time
    -0.24
    饼
    -0.24
    sch
    -0.24
    unct
    -0.24
    al
    -0.23
    æĸ°åŀĭ
    -0.23
    POSITIVE LOGITS
     Cursors
    0.31
     Almighty
    0.27
     curs
    0.26
    ×ķר×Ļ×Ŀ
    0.26
     Bryant
    0.25
    åľ¨æ¸¸æĪıä¸Ń
    0.24
    ãĥ¼ãĤ·ãĥ§ãĥ³
    0.23
    eks
    0.23
     ifndef
    0.23
    èĩªçIJĨ
    0.23
    Activations Density 0.828%

    No Known Activations