© 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. 19-TRANSCODER-HP
    7. 9515
    Prev
    Next
    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸Ģåı£æ°Ķ
    -0.29
     clearTimeout
    -0.27
    ých
    -0.26
    uil
    -0.26
    åĿıäºĭ
    -0.25
    缴æݥ影åĵį
    -0.25
    åĺ´
    -0.25
    éĢĨè¡Į
    -0.25
    çĶľç¾İ
    -0.25
    ethod
    -0.24
    POSITIVE LOGITS
    case
    0.27
     gra
    0.26
     å¼Ģ
    0.24
    ndl
    0.24
     watch
    0.24
    åĪ»
    0.24
     mee
    0.23
     surv
    0.23
    adge
    0.23
    shire
    0.23
    Activations Density 0.055%

    No Known Activations