© 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. 141620
    Prev
    Next
    INDEX
    Explanations

    Past events

    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
    Much
    -0.27
     MUCH
    -0.26
    æľŁ
    -0.25
    RB
    -0.25
    æľŁéĹ´
    -0.25
    allocation
    -0.25
     Much
    -0.25
    å±ŀå®ŀ
    -0.24
     much
    -0.24
    /~
    -0.23
    POSITIVE LOGITS
    æľĢ好æĺ¯
    0.26
     spo
    0.26
    tram
    0.25
    åĮĸè¿Ľç¨ĭ
    0.25
    ##↵
    0.24
    öz
    0.24
    éĺĪ
    0.24
    uala
    0.24
    _WS
    0.24
    thresh
    0.23
    Activations Density 13.675%

    No Known Activations