© 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. 40970
    Prev
    Next
    INDEX
    Explanations

    Reminiscing about the past

    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
    溯
    -0.30
     longest
    -0.28
     chain
    -0.28
     tracer
    -0.28
     trace
    -0.28
     continuity
    -0.27
    cente
    -0.27
    alous
    -0.27
    Chain
    -0.27
    erior
    -0.27
    POSITIVE LOGITS
    åĿĮ
    0.28
    åĢ¾æĸľ
    0.27
    ksam
    0.26
    éĢŁçİĩ
    0.26
    ä¸Ģå®ļ
    0.26
    æķ°çłģ
    0.25
    å¸ħåĵ¥
    0.25
     spotted
    0.24
    åķĨæĬ¥
    0.24
    _rs
    0.23
    Activations Density 0.610%

    No Known Activations