© 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. 27-TRANSCODER-HP
    7. 57353
    Prev
    Next
    INDEX
    Explanations

    missing data, coding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pe
    -0.28
    izin
    -0.26
    åģľ
    -0.26
    .pe
    -0.24
     gathering
    -0.24
    adal
    -0.24
    ZONE
    -0.24
     Black
    -0.24
     homes
    -0.24
     Surge
    -0.23
    POSITIVE LOGITS
    Tiny
    0.28
    éĶĻäºĨ
    0.27
    ä¸į对
    0.26
    .addField
    0.26
    incorrect
    0.26
    建档
    0.24
    éĤ£äºĽ
    0.24
    ä»»æľŁ
    0.24
    ç¡Į
    0.24
    inator
    0.24
    Activations Density 0.005%

    No Known Activations