© 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. 151444
    Prev
    Next
    INDEX
    Explanations

    scientific and technical language

    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
    ched
    -0.30
    iedo
    -0.27
    č↵    č↵
    -0.26
     ValueEventListener
    -0.25
    è·¨
    -0.25
    ja
    -0.25
    åij¢
    -0.25
     subject
    -0.25
    åİ»
    -0.24
    rimp
    -0.24
    POSITIVE LOGITS
    atorial
    0.28
    layan
    0.27
     contributing
    0.26
    ä»£è¡¨åĽ¢
    0.26
     risking
    0.26
     cooled
    0.26
    dispose
    0.24
    past
    0.24
    contrib
    0.24
    Contrib
    0.24
    Activations Density 0.930%

    No Known Activations