© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 39674
    Prev
    Next
    INDEX
    Explanations

    Italian

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
     your
    -0.28
    losures
    -0.27
     static
    -0.27
    ppe
    -0.26
    isci
    -0.26
     con
    -0.25
     expert
    -0.25
    composition
    -0.25
    Cod
    -0.25
    cznie
    -0.25
    POSITIVE LOGITS
    ÙĬض
    0.27
    éĩijèŀįåį±æľº
    0.27
     Assist
    0.26
    è¡©
    0.26
    çİĩ为
    0.26
    EEK
    0.25
    èļ©
    0.25
    梦è§ģ
    0.25
    нÑģÑĤ
    0.25
    ths
    0.24
    Activations Density 0.231%

    No Known Activations