© 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. 27-TRANSCODER-HP
    7. 58263
    Prev
    Next
    INDEX
    Explanations

    first

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -Smith
    -0.30
    coder
    -0.27
    åįĩ级
    -0.26
    溢
    -0.25
    -margin
    -0.25
     Mã
    -0.25
    ë¡Ŀ
    -0.25
    ÙĪار
    -0.24
    coli
    -0.24
    çĶµå·¥
    -0.24
    POSITIVE LOGITS
    tuple
    0.30
    åij½åIJį
    0.27
    uest
    0.27
    jen
    0.26
     dearly
    0.26
    ersions
    0.26
    åĽŀ
    0.25
    Pictures
    0.25
     openly
    0.24
     Evans
    0.24
    Activations Density 0.003%

    No Known Activations