© 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. 64194
    Prev
    Next
    INDEX
    Explanations

    Code, languages, random words

    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
    æµĥ
    -0.29
    nameof
    -0.26
    raid
    -0.26
    ertest
    -0.26
    çľ¼åīį
    -0.26
    管çIJĨåĪ¶åº¦
    -0.26
    checked
    -0.25
    Checked
    -0.25
    ibel
    -0.25
    =%.
    -0.25
    POSITIVE LOGITS
     conson
    0.30
    åĬ¿
    0.28
     combin
    0.28
    ç»ĵå°¾
    0.28
    è¾ĥéķ¿
    0.26
    转æĬĺ
    0.26
    顺åĬ¿
    0.26
     longer
    0.25
    éĩįä¸Ń
    0.25
     combined
    0.25
    Activations Density 39.444%

    No Known Activations