© 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. 141660
    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
    rica
    -0.30
    looking
    -0.28
     UNITED
    -0.27
    nge
    -0.27
    lesson
    -0.26
     geb
    -0.26
    лог
    -0.26
    ढ
    -0.25
    UNIT
    -0.25
     looking
    -0.25
    POSITIVE LOGITS
     prosper
    0.26
    åıŁ
    0.25
    |--
    0.25
    iphers
    0.24
    主æĿĥ
    0.24
    çļĦè§ĤçĤ¹
    0.24
    Material
    0.24
     #:
    0.24
    è§ĤçĤ¹
    0.24
     acknowledgement
    0.24
    Activations Density 0.172%

    No Known Activations

    This feature has no known activations.