© 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. 87922
    Prev
    Next
    INDEX
    Explanations

    Numbers in patents

    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
    Rp
    -0.27
    çľĭä¸įæĩĤ
    -0.26
     deductible
    -0.25
    åĩŃ
    -0.25
    -sum
    -0.24
     ald
    -0.24
    è¶Ĭé«ĺ
    -0.24
    bs
    -0.24
     Crist
    -0.24
    /detail
    -0.23
    POSITIVE LOGITS
     traces
    0.26
    ë¡Ģ
    0.25
     PURPOSE
    0.25
    .const
    0.24
    -grand
    0.24
    _Static
    0.23
    Launcher
    0.23
    -Russian
    0.23
    -FIRST
    0.23
     Gaz
    0.22
    Activations Density 0.012%

    No Known Activations