© 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. 56380
    Prev
    Next
    INDEX
    Explanations

    b

    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
     switched
    -0.28
    åºľ
    -0.27
    绣çŃ¹æİ¨è¿Ľ
    -0.25
    è´®
    -0.25
    .grad
    -0.24
    穹
    -0.24
    æĸ¥
    -0.24
    ä¸Ģä½ĵåĮĸ
    -0.24
    åijĬ
    -0.24
    ersist
    -0.24
    POSITIVE LOGITS
    ndon
    0.28
    cps
    0.27
    onces
    0.26
    æĽ´éĩįè¦ģçļĦ
    0.26
    nier
    0.26
    éĥ½æĥ³
    0.26
     conquer
    0.25
     arresting
    0.25
    iera
    0.24
    è··
    0.24
    Activations Density 0.111%

    No Known Activations