© 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. 111126
    Prev
    Next
    INDEX
    Explanations

    Mathematical and abstract concepts

    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
    (Console
    -0.28
    ç©¿éĢı
    -0.25
    eled
    -0.25
     Console
    -0.25
    鼶åĶ®
    -0.24
    æĶ¾è¿Ľ
    -0.24
    ugo
    -0.23
    	Console
    -0.23
    为æĤ¨æıIJä¾Ľ
    -0.23
    endant
    -0.23
    POSITIVE LOGITS
    claims
    0.25
    odies
    0.25
    mobx
    0.24
    Gl
    0.24
    SSL
    0.24
    eman
    0.23
    -Man
    0.23
    .Alpha
    0.23
     GDK
    0.23
    çģŃ亡
    0.23
    Activations Density 0.002%

    No Known Activations