© 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. 97721
    Prev
    Next
    INDEX
    Explanations

    informal internet writing

    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
    ican
    -0.27
    é¹ľ
    -0.26
    ---</
    -0.25
     hy
    -0.25
    iÄį
    -0.24
     sẻ
    -0.24
    éªĽ
    -0.24
    mun
    -0.24
     sibling
    -0.23
    ä¾ĭãģĪãģ°
    -0.23
    POSITIVE LOGITS
    åıij
    0.27
    ZE
    0.26
    á¿Ĩ
    0.26
    èĻ±
    0.25
     GI
    0.25
    *[
    0.25
    aira
    0.24
    rait
    0.24
    å¦ĸ
    0.24
    ToPoint
    0.23
    Activations Density 0.010%

    No Known Activations