© 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. 20-TRANSCODER-HP
    7. 108509
    Prev
    Next
    INDEX
    Explanations

    Investigation and analysis

    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
    Negative Logits
    izzy
    -0.26
    é¦Ĩ
    -0.25
    leness
    -0.25
    ä¸įå¿ħ
    -0.24
    åı¯ä»¥è®©
    -0.24
     mát
    -0.24
    çĶ¬
    -0.24
    ãĤ³ãĥŁãĥ¥ãĥĭãĤ±ãĥ¼ãĤ·ãĥ§ãĥ³
    -0.23
    _dispatch
    -0.23
     Hosp
    -0.23
    POSITIVE LOGITS
    /mit
    0.27
    å¯Ł
    0.27
    _VER
    0.26
    çļĦæĥħ
    0.26
    ä¸Ģåı£
    0.25
    ä¸į平衡
    0.25
    ød
    0.24
    缸åıį
    0.24
    иÑĩеÑģкой
    0.24
     Filed
    0.24
    Activations Density 22.308%

    No Known Activations