© 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. 129521
    Prev
    Next
    INDEX
    Explanations

    medication side effects

    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
    åIJ¸åıĸ
    -0.26
    emand
    -0.25
    /sites
    -0.24
    ustr
    -0.24
     Americ
    -0.24
     KL
    -0.24
    xEE
    -0.24
    éħİ
    -0.24
    essor
    -0.24
    ç®Ģ
    -0.24
    POSITIVE LOGITS
     dzi
    0.31
    ors
    0.28
    ...↵
    0.25
    ...↵↵
    0.25
    comma
    0.25
    ä¸İåIJ¦
    0.25
    çĹħçIJĨ
    0.24
    éĢĹ
    0.24
     divisions
    0.24
    _QMARK
    0.24
    Activations Density 0.032%

    No Known Activations