© 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. 8146
    Prev
    Next
    INDEX
    Explanations

    Software/Publication Code & Documentation

    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
    inging
    -0.30
    пÑĢÑı
    -0.30
    ham
    -0.29
    rut
    -0.27
    mere
    -0.26
    ä½ıéĻ¢
    -0.26
    hoe
    -0.26
    burn
    -0.25
    outine
    -0.25
    sign
    -0.24
    POSITIVE LOGITS
    ousel
    0.30
    ughs
    0.27
    Criterion
    0.26
     dubious
    0.26
    ä¾Ŀ次
    0.25
    éĢIJä¸Ģ
    0.25
     Criterion
    0.25
     thinkers
    0.25
     `[
    0.25
    marshaller
    0.24
    Activations Density 0.003%

    No Known Activations