© 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. 40163
    Prev
    Next
    INDEX
    Explanations

    Code and categories

    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
    ìŀIJëıĻ
    -0.25
    vida
    -0.25
    .creation
    -0.25
    åľºåIJĪ
    -0.24
    sky
    -0.24
    åıĮåıĮ
    -0.24
    ä¸»æľº
    -0.24
    ople
    -0.24
    èĭ¥æĤ¨
    -0.24
    ERE
    -0.23
    POSITIVE LOGITS
    å¼¢
    0.31
    ocate
    0.28
    å±Ĥ
    0.27
    agos
    0.26
    妹
    0.25
    ccd
    0.25
     yourselves
    0.24
     quart
    0.24
     hasNext
    0.24
    OutOfRange
    0.24
    Activations Density 0.455%

    No Known Activations