© 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. 9-TRANSCODER-HP
    7. 29115
    Prev
    Next
    INDEX
    Explanations

    billions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    zin
    -0.30
     circulated
    -0.28
    apol
    -0.26
     textbook
    -0.25
     пÑĢим
    -0.24
    رد
    -0.24
    æѦè£ħ
    -0.24
    vers
    -0.24
    ewn
    -0.24
     cons
    -0.24
    POSITIVE LOGITS
    anja
    0.28
    IDES
    0.28
    ernaut
    0.26
    FetchRequest
    0.25
    tv
    0.25
    _tv
    0.24
    æ¼Ĩ
    0.24
     getLocation
    0.23
    dio
    0.23
     onLoad
    0.23
    Activations Density 1.582%

    No Known Activations