© 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. 150985
    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
    .persist
    -0.28
     awaited
    -0.26
    kip
    -0.25
     Others
    -0.25
    lator
    -0.24
    Others
    -0.24
    ersistence
    -0.24
    ä¸Ģä¼ļ
    -0.24
     storyt
    -0.24
    á»ĩm
    -0.23
    POSITIVE LOGITS
    åĭĴ
    0.27
    麻çĹ¹
    0.26
    åģı
    0.26
    æŃĮè¯į
    0.25
    ety
    0.25
    åħ¨
    0.25
    çIJĨ解åĴĮ
    0.25
    enci
    0.25
    Teen
    0.25
    ãĤ¿ãĤ¤
    0.25
    Activations Density 0.274%

    No Known Activations

    This feature has no known activations.