© 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. 9450
    Prev
    Next
    INDEX
    Explanations

    this

    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
    -desc
    -0.28
    ellas
    -0.27
     ruth
    -0.26
    лиÑĤ
    -0.25
    mention
    -0.24
     Beg
    -0.24
     Listing
    -0.24
     rtl
    -0.24
    mega
    -0.23
     tir
    -0.23
    POSITIVE LOGITS
    »
    0.27
    å±Ĥåĩº
    0.26
    ç£
    0.26
    apis
    0.25
    æ´»æĢ§
    0.25
     qu
    0.25
    ubby
    0.24
    è¶Ĭ好
    0.24
    antine
    0.24
    antar
    0.24
    Activations Density 0.650%

    No Known Activations