© 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. 30-TRANSCODER-HP
    7. 96775
    Prev
    Next
    INDEX
    Explanations

    code/technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     work
    -0.33
    work
    -0.29
     team
    -0.28
    -work
    -0.27
    ä¼Ĭæĸ¯åħ°
    -0.26
     process
    -0.26
    -cultural
    -0.25
    æĺ¯ä¸Ģéĥ¨
    -0.24
    å·¥ä½ľ
    -0.24
    紧紧
    -0.24
    POSITIVE LOGITS
    conduct
    0.37
     Conduct
    0.35
     conduc
    0.33
     conduct
    0.33
     conductor
    0.30
     пÑĢов
    0.29
    anzi
    0.28
     statistic
    0.28
     conducted
    0.28
    htub
    0.27
    Activations Density 0.099%

    No Known Activations