© 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. 58374
    Prev
    Next
    INDEX
    Explanations

    Computer code

    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
    ewater
    -0.28
    (()
    -0.25
    دا
    -0.25
    scratch
    -0.25
    ר×Ļ×Ŀ
    -0.24
    åĽ½å®¶éĩįçĤ¹
    -0.24
    awn
    -0.24
    ework
    -0.24
    建åįİ
    -0.24
    erton
    -0.23
    POSITIVE LOGITS
     surv
    0.25
    æ¶ħ
    0.25
    -navigation
    0.25
    æijĦå½±
    0.25
     '~
    0.24
    icopt
    0.24
    Entities
    0.24
    oya
    0.24
    æ²ī
    0.24
    ä¸į满
    0.23
    Activations Density 0.026%

    No Known Activations