© 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. 40173
    Prev
    Next
    INDEX
    Explanations

    Machine-generated text

    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
    .cf
    -0.28
     landlord
    -0.25
    翳
    -0.25
    å¤ĸå¥Ĺ
    -0.24
    æķ·
    -0.24
     æĽ
    -0.24
    åı¦
    -0.23
    Poss
    -0.23
    稳
    -0.23
     Unary
    -0.23
    POSITIVE LOGITS
    chip
    0.26
    空æ°Ķä¸Ń
    0.26
    uct
    0.26
    anych
    0.26
    oyer
    0.25
    acho
    0.25
    _invoke
    0.25
    ã
    0.25
     crunch
    0.25
    ctica
    0.25
    Activations Density 0.058%

    No Known Activations