© 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. 27-TRANSCODER-HP
    7. 9729
    Prev
    Next
    INDEX
    Explanations

    Code and/or equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    尤为éĩįè¦ģ
    -0.28
    _EXTRA
    -0.26
    ummer
    -0.26
    iscal
    -0.26
     wicht
    -0.25
    ÃŃst
    -0.25
    è¶³å¤ŁçļĦ
    -0.24
    redits
    -0.24
    uration
    -0.24
    åħ±åIJĮä½ĵ
    -0.24
    POSITIVE LOGITS
    ç»ĵ
    0.28
    zd
    0.27
     endorse
    0.26
    åıĹ伤
    0.26
    UAL
    0.25
    but
    0.25
    à¤ĵ
    0.25
     crush
    0.24
    Fran
    0.24
     intercepted
    0.24
    Activations Density 0.006%

    No Known Activations