© 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. 20-TRANSCODER-HP
    7. 63448
    Prev
    Next
    INDEX
    Explanations

    Mixed, scientific snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .experimental
    -0.32
    åıijå±ķåİĨç¨ĭ
    -0.27
    æ¡Ī
    -0.26
    å½±åĵįåĬĽçļĦ
    -0.26
    rors
    -0.26
    enne
    -0.24
    æĸ°ä¸Ģè½®
    -0.24
    “
    -0.24
    uploads
    -0.24
    åıijå±ķæĸ¹åIJij
    -0.24
    POSITIVE LOGITS
    oked
    0.28
    ilet
    0.28
     yi
    0.27
     iy
    0.27
    -exc
    0.24
    tit
    0.24
    .sig
    0.23
    ']+
    0.23
     firing
    0.23
    .secret
    0.23
    Activations Density 18.406%

    No Known Activations