© 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. 24-TRANSCODER-HP
    7. 151411
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åºĶ对
    -0.28
     Manual
    -0.28
     iss
    -0.28
    pane
    -0.27
    ister
    -0.26
    steen
    -0.26
    arris
    -0.26
    contre
    -0.25
     agency
    -0.25
     identity
    -0.25
    POSITIVE LOGITS
    uÅŁ
    0.25
    _tem
    0.25
    åľ¨è¿ĩ渡
    0.25
    =%.
    0.24
     TAM
    0.24
    æ¼ķ
    0.24
     %-
    0.24
    åĭĩæķ¢
    0.24
    -SA
    0.24
     %=
    0.24
    Activations Density 0.047%

    No Known Activations