© 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. 23-TRANSCODER-HP
    7. 25467
    Prev
    Next
    INDEX
    Explanations

    help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    stim
    -0.29
    Forms
    -0.28
    è¦ģèĢĥèĻij
    -0.26
    feeds
    -0.26
    ä¹ĭ家
    -0.25
    羸
    -0.25
     <<↵
    -0.25
    вÑıз
    -0.25
    rates
    -0.25
    Interaction
    -0.25
    POSITIVE LOGITS
    åħ¬åijĬ
    0.27
    inity
    0.26
    inan
    0.26
     sort
    0.25
     Rue
    0.25
    (ur
    0.24
     belonged
    0.24
    /exec
    0.24
     гоÑĤов
    0.24
    Ur
    0.24
    Activations Density 0.007%

    No Known Activations