© 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. 7768
    Prev
    Next
    INDEX
    Explanations

    November dates

    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
    Negative Logits
    ntag
    -0.26
    \Facades
    -0.26
    :Array
    -0.26
    amage
    -0.26
    ä¸Ńæĸ°ç½ij
    -0.25
    ashes
    -0.25
    åĿĮ
    -0.24
    mony
    -0.24
    uco
    -0.24
    GetObject
    -0.23
    POSITIVE LOGITS
    cron
    0.26
    hay
    0.26
    cro
    0.26
    MES
    0.25
    iginal
    0.25
    rit
    0.24
    slice
    0.24
    临æŶ
    0.24
    izar
    0.23
     Loose
    0.23
    Activations Density 0.005%

    No Known Activations