© 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. 14-TRANSCODER-HP
    7. 40258
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eaten
    -0.28
    cko
    -0.27
    ibre
    -0.26
    ruk
    -0.26
    åĿļå®ļä¸į移
    -0.25
     Fav
    -0.25
    Æ°á»Ŀ
    -0.25
    hani
    -0.24
     kino
    -0.24
    erg
    -0.24
    POSITIVE LOGITS
    dna
    0.28
     DNA
    0.27
    .addClass
    0.27
    DNA
    0.26
    .addRow
    0.26
    è§ĩ
    0.25
    -angular
    0.25
    -mask
    0.25
    çļĦæľºä¼ļ
    0.24
    æĭħ
    0.24
    Activations Density 0.248%

    No Known Activations

    This feature has no known activations.