© 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. 23360
    Prev
    Next
    INDEX
    Explanations

    so

    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
    并ä¸İ
    -0.27
    åı¸
    -0.27
     ob
    -0.27
    使å¾Ĺ
    -0.25
     enough
    -0.25
     action
    -0.24
    并
    -0.24
    ixmap
    -0.24
     ArrayList
    -0.24
     sab
    -0.24
    POSITIVE LOGITS
    ÃŃc
    0.28
    é¦Ī
    0.27
    åıĪ被
    0.27
    azu
    0.26
    UTC
    0.26
    atus
    0.25
     moreover
    0.25
    åħĪæĬĬ
    0.25
    JV
    0.25
    主è¦ģåİŁåĽł
    0.25
    Activations Density 0.006%

    No Known Activations