© 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. 63728
    Prev
    Next
    INDEX
    Explanations

    Humans

    np_max-act · gemini-2.0-flash
    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
    ah
    -0.26
     transfer
    -0.26
    kom
    -0.25
    cca
    -0.25
     km
    -0.25
    ne
    -0.25
    è°¦
    -0.25
    -transfer
    -0.24
     er
    -0.24
    ä¸ĩæĪ·
    -0.24
    POSITIVE LOGITS
    èĭ
    0.28
    ä¸Ģæŀļ
    0.26
     &_
    0.25
    ä¸Ģåı°
    0.25
    åĸĭ
    0.24
     #↵↵
    0.24
     sticking
    0.24
    ctxt
    0.24
    zend
    0.24
     impecc
    0.24
    Activations Density 6.680%

    No Known Activations