© 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. 129084
    Prev
    Next
    INDEX
    Explanations

    Access

    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
    åĪºå®¢
    -0.27
    _due
    -0.27
    seau
    -0.26
    ILD
    -0.26
    ục
    -0.25
    andler
    -0.24
    ä¹ħä¹ħ
    -0.24
    xDB
    -0.24
    hani
    -0.24
     honeymoon
    -0.23
    POSITIVE LOGITS
     overriding
    0.31
     overridden
    0.31
    é»ĺ认
    0.31
    åı¯ä»¥çĽ´æİ¥
    0.30
     default
    0.30
     override
    0.29
    åİ¿éķ¿
    0.29
    å·¥å§Ķ
    0.29
     available
    0.28
     usage
    0.28
    Activations Density 0.073%

    No Known Activations