© 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. 129764
    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
     setC
    -0.27
    ore
    -0.26
    解åĨ³
    -0.25
    åľº
    -0.25
    åĢĴåľ¨
    -0.25
    .substr
    -0.24
    éĹŃ
    -0.24
    åıĤè°ĭ
    -0.23
    åŁºåľ°
    -0.23
    è¾°
    -0.23
    POSITIVE LOGITS
    è´¬åĢ¼
    0.29
     ÑģÑĤÑĢа
    0.26
    åħ¼ä»»
    0.25
     presentation
    0.25
    resentation
    0.25
    notes
    0.25
     гаÑĢ
    0.24
    ãĤ³ãĥĶãĥ¼
    0.24
    æĴ¤éĶĢ
    0.24
    hon
    0.24
    Activations Density 73.639%

    No Known Activations

    This feature has no known activations.