© 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. 33-TRANSCODER-HP
    7. 52793
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     des
    -0.33
     XK
    -0.29
     dich
    -0.27
    Des
    -0.27
     kì
    -0.26
     migr
    -0.26
     hand
    -0.26
    éģĵ
    -0.26
     assumed
    -0.26
    éĢ¡
    -0.26
    POSITIVE LOGITS
     plain
    0.27
     -:
    0.27
    æŃ£å¸¸ä½¿çĶ¨
    0.27
    uez
    0.26
    ivel
    0.26
     #:
    0.26
    hof
    0.25
     Plain
    0.25
    عاÙĦ
    0.25
    perPage
    0.25
    Activations Density 0.004%

    No Known Activations