© 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. 12-TRANSCODER-HP
    7. 23444
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸į认è¯Ĩ
    -0.26
    -ren
    -0.25
    ième
    -0.25
     placements
    -0.25
    ä¼ļ对
    -0.25
    fo
    -0.25
    icht
    -0.25
     am
    -0.24
    çķĪ
    -0.24
    趴
    -0.24
    POSITIVE LOGITS
    ADB
    0.26
    è°
    0.26
     corrobor
    0.24
    å©ļ
    0.24
    stä
    0.24
    persistent
    0.23
    ukt
    0.23
    ghan
    0.23
    å¼¹
    0.23
    iges
    0.23
    Activations Density 0.004%

    No Known Activations