© 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. 150100
    Prev
    Next
    INDEX
    Explanations

    say ")"

    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
    ç¨İçİĩ
    -0.27
    çĶ¨æĪ·åIJį
    -0.25
    .locale
    -0.25
    产åĵģ
    -0.25
     ton
    -0.25
    زاÙĦ
    -0.24
    /products
    -0.23
     Categoria
    -0.23
    ç»Ģ
    -0.23
    locale
    -0.23
    POSITIVE LOGITS
     fulfil
    0.29
    loit
    0.26
    _cores
    0.25
     jobId
    0.25
     critically
    0.25
    iola
    0.25
     JOB
    0.24
     MPH
    0.24
    DI
    0.24
    elong
    0.24
    Activations Density 0.898%

    No Known Activations