© 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. 32-TRANSCODER-HP
    7. 41561
    Prev
    Next
    INDEX
    Explanations

    Code and foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lay
    -0.29
    å°ıé¾Ļ
    -0.28
    ved
    -0.28
     dam
    -0.27
    ÅĤam
    -0.26
    anden
    -0.25
     ado
    -0.25
    bright
    -0.25
    èı±
    -0.25
    ca
    -0.24
    POSITIVE LOGITS
    å®ŀ
    0.28
    å®ŀä¹ł
    0.27
    åıĭ
    0.26
    實
    0.25
    -html
    0.25
    æĮģ
    0.25
    æĹ¶è¾°
    0.25
    åĵģè´¨
    0.24
     Ernst
    0.24
     tack
    0.23
    Activations Density 0.001%

    No Known Activations