© 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. 20-TRANSCODER-HP
    7. 142130
    Prev
    Next
    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç§ĥ
    -0.29
    odd
    -0.28
    æĺŁæľŁ
    -0.27
     xlink
    -0.27
     heat
    -0.26
    uppy
    -0.25
    å¥ĩ
    -0.25
    æİ¢
    -0.25
    yled
    -0.24
    ë°ķ
    -0.24
    POSITIVE LOGITS
     coma
    0.29
    绣绣
    0.26
     impl
    0.25
     later
    0.25
    åħĪæĬĬ
    0.25
    ç»Ĩç»Ĩ
    0.24
    InstanceState
    0.24
     neatly
    0.24
    inic
    0.24
    rss
    0.24
    Activations Density 13.491%

    No Known Activations