© 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. 31-TRANSCODER-HP
    7. 18592
    Prev
    Next
    INDEX
    Explanations

    health studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     among
    -2.03
    among
    -1.87
     amongst
    -1.71
     Among
    -1.70
    Among
    -1.58
     ÑģÑĢеди
    -1.39
    åħ¶ä¸Ń
    -1.11
    åħ¶ä¸Ńæľī
    -0.87
     wÅĽród
    -0.81
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.80
    POSITIVE LOGITS
    cke
    0.29
    ise
    0.27
    åıĮèħ¿
    0.27
    çļĦä¸ĢåĪĩ
    0.24
    .removeAll
    0.24
    åĩºåĩ»
    0.24
    tabpanel
    0.23
    beck
    0.23
    /reset
    0.23
    uth
    0.23
    Activations Density 1.459%

    No Known Activations