© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 87119
    Prev
    Next
    INDEX
    Explanations

    Stock ticker symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĻįä½İæĪIJæľ¬
    -0.27
     scal
    -0.25
    çĶ«
    -0.25
    é»ijçĻ½
    -0.25
    ä¸Ģ次æĢ§
    -0.24
    å°±ä¸ļå²Ĺä½į
    -0.23
     context
    -0.23
     pictured
    -0.23
    _ctx
    -0.23
     fines
    -0.23
    POSITIVE LOGITS
    ç»Ĥ
    0.29
     Responsible
    0.26
    enting
    0.25
     Committee
    0.25
    agen
    0.24
    å§Ķåijĺä¼ļ
    0.24
    лан
    0.24
     conce
    0.24
     Advis
    0.24
    VERT
    0.23
    Activations Density 0.010%

    No Known Activations