© 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. 9849
    Prev
    Next
    INDEX
    Explanations

    code-related text

    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
    uper
    -0.27
    .biz
    -0.26
     rugs
    -0.25
    á»Ļng
    -0.25
     scram
    -0.25
    ignon
    -0.25
     hops
    -0.25
    ing
    -0.24
     beauty
    -0.23
    ispens
    -0.23
    POSITIVE LOGITS
     GENERATED
    0.28
    oot
    0.27
    æĸ°éĻĪ代谢
    0.24
    pad
    0.24
    hir
    0.24
    ilities
    0.24
    çĸ
    0.24
    èĥ½æī¾åĪ°
    0.24
     correspondence
    0.24
    åѦåĪ°
    0.24
    Activations Density 0.016%

    No Known Activations