© 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. 64078
    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
    ä¸įä¸Ĭ
    -0.26
     BS
    -0.24
    å°Ķ
    -0.24
    usp
    -0.23
    PS
    -0.23
    æ¹¾
    -0.23
    æ³Ĭ
    -0.23
    çģ£
    -0.23
    already
    -0.23
    åĪ©çĶ¨
    -0.23
    POSITIVE LOGITS
    tsy
    0.28
    mers
    0.27
    pipes
    0.26
    OptionsMenu
    0.25
    кÑĢаÑĤ
    0.24
    nge
    0.23
    ä¼¼ä¹İæĺ¯
    0.23
    inati
    0.23
    asmus
    0.23
    ä¸į论æĺ¯
    0.23
    Activations Density 23.495%

    No Known Activations

    This feature has no known activations.