© 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. 25-TRANSCODER-HP
    7. 107011
    Prev
    Next
    INDEX
    Explanations

    By/J

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    塾
    -0.27
    åıĹæįŁ
    -0.27
     locom
    -0.26
    æĶ¶
    -0.26
    讹
    -0.26
    åĬ¡å·¥
    -0.25
    大人
    -0.25
    errer
    -0.24
    伤害
    -0.24
    è°¢
    -0.24
    POSITIVE LOGITS
    ä¸Ģ个å¤ļ
    0.27
    ","+
    0.27
    instrument
    0.27
    MATRIX
    0.26
    Lens
    0.26
    modo
    0.26
    çļĦæĵįä½ľ
    0.26
    ikel
    0.25
    ç«
    0.24
     instrument
    0.24
    Activations Density 0.157%

    No Known Activations