© 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. 20-TRANSCODER-HP
    7. 141719
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    责任ç¼ĸè¾ij
    -0.26
    æī«ä¸Ģæī«
    -0.25
    gebra
    -0.24
     ste
    -0.24
    äºĨä¸Ģä¸ĭ
    -0.23
    ved
    -0.23
    çĶ»çĶ»
    -0.23
    è¡Įãģı
    -0.23
     Av
    -0.23
     bure
    -0.23
    POSITIVE LOGITS
    ä½ı
    0.27
    reo
    0.27
    ecz
    0.27
    око
    0.25
    cff
    0.25
    çŁ
    0.25
     screwed
    0.25
     hô
    0.25
     Letter
    0.24
    eneg
    0.24
    Activations Density 39.632%

    No Known Activations

    This feature has no known activations.