© 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. 40434
    Prev
    Next
    INDEX
    Explanations

    sudden

    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
     favor
    -0.28
     torn
    -0.28
    rogram
    -0.28
     '{{
    -0.27
    纲
    -0.27
    monkey
    -0.27
    大ä¼ļ
    -0.26
    rough
    -0.26
    åħ¸
    -0.26
     favour
    -0.25
    POSITIVE LOGITS
    itical
    0.27
    身价
    0.26
    iginal
    0.26
    inear
    0.26
    ÃŃm
    0.26
    é¹ĥ
    0.25
    _plural
    0.25
    ä¼ĹæīĢ
    0.24
    boundary
    0.24
     rek
    0.24
    Activations Density 0.619%

    No Known Activations