© 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. 129984
    Prev
    Next
    INDEX
    Explanations

    People's names

    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
    å¯Įæľī
    -0.27
    ina
    -0.26
    (*
    -0.26
    INA
    -0.26
    {{{
    -0.26
    ANO
    -0.25
     hole
    -0.24
    è¿IJ
    -0.23
    æĹģ
    -0.23
    hole
    -0.23
    POSITIVE LOGITS
    deg
    0.28
    éĩĮæĸ¯
    0.25
    ï¼īãĢģ
    0.25
    ãĢĨ
    0.24
     mens
    0.24
    usting
    0.24
    åĽŀäºĭ
    0.24
    祥
    0.23
    ienie
    0.23
    elix
    0.23
    Activations Density 0.712%

    No Known Activations