© 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. 149822
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éĹª
    -0.32
    åİŁåĽłä¹ĭä¸Ģ
    -0.26
    umbo
    -0.25
    mol
    -0.24
    uating
    -0.24
     Grat
    -0.23
    ymi
    -0.23
    asured
    -0.23
     Attribution
    -0.23
    å®Īä½ı
    -0.23
    POSITIVE LOGITS
     Ih
    0.25
    eri
    0.23
     discrimin
    0.23
     Irving
    0.23
     budgets
    0.23
    media
    0.23
    _Impl
    0.23
     regimes
    0.23
     cou
    0.23
    ApplicationContext
    0.23
    Activations Density 0.026%

    No Known Activations

    This feature has no known activations.