© 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. 150458
    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
    edImage
    -0.28
    å®īè£ħ
    -0.28
    æĢ»çļĦ
    -0.27
    кÑĢа
    -0.27
    install
    -0.26
    inan
    -0.26
     >",
    -0.26
    efa
    -0.25
    å³Ĵ
    -0.25
    æµĨ
    -0.24
    POSITIVE LOGITS
    åĩºæīĭ
    0.34
     Kund
    0.29
    ä»»æľŁ
    0.28
     courtesy
    0.27
     deeds
    0.24
    责任åĪ¶
    0.24
    çijķçĸµ
    0.24
    .nextSibling
    0.23
    Mods
    0.23
    çĿĢæīĭ
    0.23
    Activations Density 0.103%

    No Known Activations

    This feature has no known activations.