© 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. 150743
    Prev
    Next
    INDEX
    Explanations

    technical/mathematical 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
    ä¹ĭåĬ¿
    -0.29
    åĨħ
    -0.27
    UNCT
    -0.26
    èIJ½åľ¨
    -0.26
     MIL
    -0.26
    akedown
    -0.25
    èIJ½åĪ°
    -0.24
    æĿ¥èĩª
    -0.24
    ANTA
    -0.24
    .Classes
    -0.24
    POSITIVE LOGITS
     Ones
    0.27
     Egg
    0.26
    еп
    0.26
    §
    0.25
    é«ĺå±Ĥ次
    0.24
     geliÅŁtir
    0.24
    åĬ³åĬ¡æ´¾éģ£
    0.23
     hexadecimal
    0.23
     ones
    0.23
     negative
    0.23
    Activations Density 0.907%

    No Known Activations