© 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. 41114
    Prev
    Next
    INDEX
    Explanations

    Ends in "er" or "Lear"

    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
    reten
    -0.33
    {i
    -0.28
    Ki
    -0.27
     compl
    -0.27
    æįº
    -0.24
    .Features
    -0.24
     NDEBUG
    -0.24
    Lite
    -0.24
    rus
    -0.24
     sammen
    -0.23
    POSITIVE LOGITS
     redirected
    0.28
    åıĪ被
    0.27
    ugh
    0.26
     nonexistent
    0.26
     misplaced
    0.26
    åĪĨæķ£
    0.26
    ä¸į足
    0.25
     footing
    0.25
    study
    0.25
    å¹¿æ³Ľ
    0.25
    Activations Density 1.236%

    No Known Activations