© 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. 25566
    Prev
    Next
    INDEX
    Explanations

    like

    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
    产åĵģçļĦ
    -0.30
    产åĵģè´¨éĩı
    -0.25
    æĦı大
    -0.25
    交éĢļäºĭæķħ
    -0.25
    æĪijåıĪ
    -0.25
    çļĦ身份
    -0.25
    ita
    -0.24
    ailed
    -0.24
    engo
    -0.24
    æłijèĦĤ
    -0.24
    POSITIVE LOGITS
     because
    0.31
    åĽłä¸º
    0.29
     however
    0.27
    åĽłåħ¶
    0.26
     cuz
    0.26
     unlike
    0.25
    æİ¥
    0.25
    because
    0.24
    Frame
    0.24
     indeed
    0.24
    Activations Density 0.034%

    No Known Activations