© 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. 57181
    Prev
    Next
    INDEX
    Explanations

    Code and data snippets

    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
    spir
    -0.28
    å¥łåŁº
    -0.28
     bench
    -0.27
    ground
    -0.27
    -powered
    -0.26
    åºķå±Ĥ
    -0.26
     female
    -0.26
    æĭ¼éŁ³
    -0.25
    .setStyle
    -0.25
    kish
    -0.25
    POSITIVE LOGITS
    ãĥ©ãĤ¤ãĥĪ
    0.31
    iar
    0.28
    è¶Ĭ大
    0.28
    irty
    0.27
    大家åĪĨ享
    0.27
     TSR
    0.26
    annt
    0.26
     Redistribution
    0.26
    encion
    0.25
     OPTIONAL
    0.25
    Activations Density 0.001%

    No Known Activations