© 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. 20-TRANSCODER-HP
    7. 142403
    Prev
    Next
    INDEX
    Explanations

    medical/scientific contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     woo
    -0.31
    诱
    -0.29
    æĿijéĩĮ
    -0.28
    çī¹èī²çļĦ
    -0.27
    毫
    -0.26
    unde
    -0.26
    çĶŁåĬ¨
    -0.26
    âĨIJ
    -0.25
    aware
    -0.25
     âĨIJ
    -0.25
    POSITIVE LOGITS
    adecimal
    0.28
     билеÑĤ
    0.24
    {o
    0.24
    pps
    0.23
    imity
    0.23
    è¦ģç´§
    0.23
    aurus
    0.23
    pected
    0.23
    isseur
    0.23
     TSRMLS
    0.23
    Activations Density 59.254%

    No Known Activations