© 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. 150782
    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
    ặng
    -0.30
    管çIJĨä¸Ńå¿ĥ
    -0.29
     Benedict
    -0.26
    BOSE
    -0.26
    ENTER
    -0.26
     adaptive
    -0.25
    é«ĺæķĪ
    -0.25
    ault
    -0.24
    ESC
    -0.23
    çªĹåı£
    -0.23
    POSITIVE LOGITS
    .gstatic
    0.28
     UIL
    0.27
     pkg
    0.25
    eel
    0.24
    /copyleft
    0.24
    åįģ个
    0.24
    æĨ¬
    0.24
    straint
    0.23
    å©Ĩå©Ĩ
    0.23
    åijĬ
    0.23
    Activations Density 0.979%

    No Known Activations

    This feature has no known activations.