© 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. 40158
    Prev
    Next
    INDEX
    Explanations

    commas, parentheses

    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
    Not in Any Lists

    No Comments

    Negative Logits
    .tf
    -0.30
    åı¯æĢķçļĦ
    -0.25
    åĪĨåĪ«ä¸º
    -0.25
     Tet
    -0.24
    Tube
    -0.24
    )[-
    -0.24
    é¢Ŀ头
    -0.24
    æĬ½å¥ĸ
    -0.23
    éĤ¹
    -0.23
    BN
    -0.23
    POSITIVE LOGITS
     Hal
    0.26
    again
    0.24
     Roland
    0.24
    åŃĺ
    0.24
    ocoder
    0.24
    .collections
    0.23
    licence
    0.23
    继ç»Ńä¿ĿæĮģ
    0.23
    SuppressLint
    0.23
     chá»ĵng
    0.23
    Activations Density 0.022%

    No Known Activations