© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 150737
    Prev
    Next
    INDEX
    Explanations

    uploading

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĪ®
    -0.30
    ủy
    -0.28
    unts
    -0.26
     Sark
    -0.26
     Bookmark
    -0.25
     shortest
    -0.25
    lots
    -0.24
    hift
    -0.24
    rays
    -0.24
     dynamics
    -0.24
    POSITIVE LOGITS
    edImage
    0.33
     csvfile
    0.31
    udeau
    0.31
    DRV
    0.30
     CSV
    0.29
    myfile
    0.29
    ftp
    0.28
    PDF
    0.27
    UPLOAD
    0.27
     csv
    0.27
    Activations Density 1.397%

    No Known Activations