© 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. 99164
    Prev
    Next
    INDEX
    Explanations

    progress and improvements

    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
    åĺ´å·´
    -0.26
     Amar
    -0.24
    enco
    -0.24
    å¼Ģ头
    -0.24
    æIJŃæ¡£
    -0.23
    azar
    -0.23
    ↵     ↵
    -0.23
    stellen
    -0.23
     sticking
    -0.23
     accompagn
    -0.23
    POSITIVE LOGITS
    -inter
    0.26
    ITES
    0.25
     диаг
    0.25
    pee
    0.24
    Ĭ¶
    0.24
    ergic
    0.23
    è§īå¾Ĺ
    0.23
    cg
    0.23
     grav
    0.23
    ÄĻ
    0.23
    Activations Density 0.005%

    No Known Activations