© 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. 27-TRANSCODER-HP
    7. 57501
    Prev
    Next
    INDEX
    Explanations

    deadline

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĸ°åĮº
    -0.26
    rawer
    -0.24
    reserve
    -0.24
    éķIJ
    -0.24
    ulkan
    -0.24
    åľ°ä½į
    -0.24
    ç»ŀ
    -0.24
    ool
    -0.24
    ograd
    -0.24
    shall
    -0.23
    POSITIVE LOGITS
    paint
    0.24
    entry
    0.24
    edly
    0.23
     Entries
    0.23
     cruz
    0.23
    -entry
    0.22
    gü
    0.22
    bk
    0.22
    å¹²äºĭ
    0.22
     camping
    0.22
    Activations Density 0.013%

    No Known Activations