© 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. 22-TRANSCODER-HP
    7. 97874
    Prev
    Next
    INDEX
    Explanations

    News publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trip
    -0.30
    -switch
    -0.27
    ä¸İåıijå±ķ
    -0.26
    æľ¬èº«
    -0.26
    fully
    -0.25
    trip
    -0.25
    aty
    -0.24
     Ches
    -0.24
     idi
    -0.23
    å·´å·´
    -0.23
    POSITIVE LOGITS
    rost
    0.25
    ousand
    0.24
    è¿Ļéĥ¨
    0.24
    Ã¤ÃŁ
    0.24
    Ỿ
    0.23
    health
    0.23
    hora
    0.23
    ±Ð¾ÑĤ
    0.23
    âłĢ
    0.23
     __________________________________
    0.22
    Activations Density 0.018%

    No Known Activations