© 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. 12-TRANSCODER-HP
    7. 21998
    Prev
    Next
    INDEX
    Explanations

    Website and online sales

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è·Ĺ
    -0.31
    èĥľåĪ©
    -0.26
    æĢĿ念
    -0.26
    æĢĥ
    -0.26
    æ¡ħ
    -0.25
     another
    -0.25
    èļĤ
    -0.24
    (inv
    -0.24
    åı¦ä¸Ģ
    -0.24
    çłĶ究表æĺİ
    -0.24
    POSITIVE LOGITS
    pha
    0.29
    å³°
    0.25
    æŶæĬ¥
    0.25
    å¯ĦãģĽ
    0.24
    timezone
    0.24
    ISIBLE
    0.23
     obliged
    0.23
    varchar
    0.23
    cea
    0.23
     Intervention
    0.23
    Activations Density 0.001%

    No Known Activations