© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 86747
    Prev
    Next
    INDEX
    Explanations

    Wikipedia articles

    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
    Negative Logits
    circle
    -0.27
    æŁIJç§į
    -0.26
     noqa
    -0.25
    atk
    -0.24
    èµ·èįī
    -0.23
     Hague
    -0.23
    åľ¨è¿Ļ
    -0.23
    æŁIJäºĽ
    -0.23
    åľ¨ä»ĸçļĦ
    -0.23
     McM
    -0.23
    POSITIVE LOGITS
    onas
    0.26
    aison
    0.26
    eson
    0.25
    mitter
    0.25
    Lists
    0.25
    agus
    0.25
     doubly
    0.24
     #%
    0.24
    è£Ł
    0.23
    amework
    0.23
    Activations Density 0.036%

    No Known Activations