© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 17757
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Negative Logits
    ife
    -0.35
    ereo
    -0.33
    çļĦçĶŁåij½
    -0.31
     lifes
    -0.29
    IFE
    -0.29
    ä¸ĸä¸Ĭ
    -0.28
     lists
    -0.28
     life
    -0.28
    ifes
    -0.28
    ereg
    -0.28
    POSITIVE LOGITS
     Equ
    0.30
    Equ
    0.30
    Prime
    0.30
     approached
    0.29
     equ
    0.28
     horns
    0.28
    equ
    0.28
    对æłĩ
    0.27
    éĴ©
    0.27
    appa
    0.26
    Activations Density 0.190%

    No Known Activations