© 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. 149744
    Prev
    Next
    INDEX
    Explanations

    companies, services, products

    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
    è¿Ļä¸Ģ天
    -0.27
     dziaÅĤ
    -0.26
    STRUCTOR
    -0.25
    åĿĿ
    -0.25
     PLAY
    -0.25
    ensitive
    -0.25
     anyway
    -0.25
     bol
    -0.25
    ÅĤuż
    -0.24
    .which
    -0.24
    POSITIVE LOGITS
    onom
    0.30
    amp
    0.27
    avic
    0.27
    orman
    0.26
    udu
    0.26
    海绵
    0.26
     sách
    0.26
    evil
    0.25
    GRES
    0.25
     neurological
    0.24
    Activations Density 0.921%

    No Known Activations