© 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. 108792
    Prev
    Next
    INDEX
    Explanations

    Numbers and references

    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
    Negative Logits
    round
    -0.27
     deform
    -0.27
    ount
    -0.25
    åıĺå½¢
    -0.25
    (round
    -0.25
    conte
    -0.25
    »
    -0.24
     Powered
    -0.24
     additive
    -0.24
    Contained
    -0.24
    POSITIVE LOGITS
    ç§įåŃIJ
    0.26
    iqueta
    0.25
     Bris
    0.24
    ãĤģãģ¦
    0.24
    inite
    0.24
    ocese
    0.24
     Nurs
    0.24
    edly
    0.23
    æİĴæ¯Ĵ
    0.23
    TRACK
    0.23
    Activations Density 0.312%

    No Known Activations