© 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. 150095
    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
    liches
    -0.28
    .Parameter
    -0.26
    åĨł
    -0.26
     Accessed
    -0.26
    å¥ĩ
    -0.25
    éļ¾å¾Ĺ
    -0.25
    oop
    -0.24
    ζ
    -0.24
    empo
    -0.23
    opes
    -0.23
    POSITIVE LOGITS
    çĭ©
    0.32
    åħ¬è®¤çļĦ
    0.29
    atures
    0.28
    bulk
    0.28
    ITIONS
    0.27
    harma
    0.27
    itions
    0.26
    ificaciones
    0.26
    %/
    0.26
    nings
    0.25
    Activations Density 3.211%

    No Known Activations

    This feature has no known activations.