© 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. 64426
    Prev
    Next
    INDEX
    Explanations

    Stages of life

    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
    æİĴ
    -0.27
    çļĦèĢģ
    -0.26
    _tpl
    -0.25
    ulan
    -0.25
    .STATE
    -0.24
    éģĵ
    -0.24
    ä¸Ĭ游
    -0.24
    middle
    -0.23
    åıĮéĩį
    -0.23
    æľīæĦı
    -0.23
    POSITIVE LOGITS
    0.33
     peoples
    0.30
    _accuracy
    0.25
    åħ¨ç¤¾ä¼ļ
    0.25
    åij½ä¸Ń
    0.24
     Conversation
    0.24
    该åħ¬åı¸
    0.24
    俾
    0.24
    æľĭåıĭ
    0.24
     sacrificed
    0.24
    Activations Density 4.665%

    No Known Activations