© 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. 52860
    Prev
    Next
    INDEX
    Explanations

    both

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä»ĸ们ä¼ļ
    -0.29
    ä½į
    -0.27
     Há»į
    -0.26
    ä»·
    -0.25
     confirm
    -0.25
     endpoint
    -0.24
    ä»ĸ们
    -0.24
     account
    -0.24
    ãĥįãĤ¿
    -0.24
     They
    -0.24
    POSITIVE LOGITS
     surfaces
    0.30
     bottoms
    0.29
    laus
    0.27
     fore
    0.26
    æĭ©
    0.26
     charts
    0.26
    åĮħåĮħ
    0.26
     shells
    0.25
    西è£ħ
    0.25
    lan
    0.25
    Activations Density 0.027%

    No Known Activations