© 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. 39933
    Prev
    Next
    INDEX
    Explanations

    Scientific and technical

    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
    åij¤
    -0.26
    äºĨä¸Ģåı£
    -0.25
    pering
    -0.25
    alis
    -0.25
    inar
    -0.24
     Panel
    -0.24
    _PANEL
    -0.24
    usal
    -0.24
    _panel
    -0.24
    åĩºçĤī
    -0.24
    POSITIVE LOGITS
    头
    0.27
     glue
    0.26
    acle
    0.26
    å¥Ħ
    0.26
     Brock
    0.26
    cycl
    0.25
     Heads
    0.25
    head
    0.25
     Near
    0.24
     eventually
    0.24
    Activations Density 1.859%

    No Known Activations