© 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. 108189
    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
    åıįæŃ£
    -0.28
    紧紧
    -0.25
    好åĥıæĺ¯
    -0.24
     обÑĢаÑīа
    -0.24
    PDO
    -0.23
    ä¸įæİĴéĻ¤
    -0.23
    çģ°
    -0.23
     toughest
    -0.23
    对å¾ħ
    -0.22
     complains
    -0.21
    POSITIVE LOGITS
    truth
    0.27
     truth
    0.26
     neglig
    0.25
    èĨ³
    0.25
     ly
    0.24
    èıľ
    0.24
    è§ħ
    0.23
    eldo
    0.23
    URN
    0.23
     lens
    0.23
    Activations Density 8.413%

    No Known Activations

    This feature has no known activations.