© 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. 107827
    Prev
    Next
    INDEX
    Explanations

    Ending Up

    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
     popover
    -0.28
    å°¤åħ¶æĺ¯
    -0.28
    orum
    -0.28
    é«ĺäºİ
    -0.27
    anke
    -0.27
    /octet
    -0.26
    ä¼ļåľ¨
    -0.26
    ulty
    -0.25
     yes
    -0.25
    haps
    -0.24
    POSITIVE LOGITS
     acc
    0.27
     HBO
    0.27
    Together
    0.27
     cru
    0.25
     Enough
    0.24
    _PB
    0.24
    ç¬ij
    0.24
     effortlessly
    0.23
    åŁ
    0.23
     MessageBoxButton
    0.23
    Activations Density 10.641%

    No Known Activations