© 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. 41229
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    -parser
    -0.27
     witnessed
    -0.26
    åĪ¸
    -0.26
    ifo
    -0.25
    bens
    -0.25
    iform
    -0.25
    bled
    -0.24
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.24
     witnessing
    -0.23
    份
    -0.23
    POSITIVE LOGITS
    -degree
    0.27
    TestMethod
    0.27
    degree
    0.27
    onga
    0.27
     Degree
    0.26
    Ã¼ÃŁ
    0.26
     degrees
    0.26
    atherine
    0.26
    tra
    0.25
    è½®
    0.24
    Activations Density 0.074%

    No Known Activations

    This feature has no known activations.