© 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. 18950
    Prev
    Next
    INDEX
    Explanations

    code snippets, files, web

    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
    _GLOBAL
    -0.28
    æºĸ
    -0.26
    åĩĨ
    -0.25
    åıĮåIJij
    -0.25
    thal
    -0.25
    inta
    -0.25
    tur
    -0.24
     upside
    -0.24
     thumbs
    -0.24
     klass
    -0.23
    POSITIVE LOGITS
     Pon
    0.29
    rix
    0.25
    ä¸įä¿¡
    0.25
    æİĴéĺŁ
    0.25
    ToDo
    0.24
     ring
    0.23
    å¨ģåĬĽ
    0.23
     hinges
    0.23
     sÃŃ
    0.23
    äºĶåħŃ
    0.23
    Activations Density 0.480%

    No Known Activations