© 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. 150213
    Prev
    Next
    INDEX
    Explanations

    Adjectives, numbers, and descriptions

    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
     Gaul
    -0.26
    irth
    -0.24
    redits
    -0.23
    æīĵåĩº
    -0.23
    ä¸įå°½
    -0.23
     sach
    -0.23
     spoken
    -0.23
    ughter
    -0.23
    è¿«åĪĩ
    -0.23
    urg
    -0.22
    POSITIVE LOGITS
    OUS
    0.26
    uze
    0.25
    èĥİ
    0.24
    é¬ĵ
    0.24
     λ
    0.23
    izen
    0.23
    ETY
    0.23
     computing
    0.23
    eat
    0.23
    edException
    0.23
    Activations Density 0.730%

    No Known Activations