© 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. 129180
    Prev
    Next
    INDEX
    Explanations

    Numbers and percentages

    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
     looping
    -0.31
     ",",
    -0.26
     Ef
    -0.25
    edo
    -0.25
     LEN
    -0.25
     aud
    -0.24
     sham
    -0.24
     };↵↵↵
    -0.24
    Ĥ¤
    -0.24
     arriving
    -0.24
    POSITIVE LOGITS
    utable
    0.31
    acre
    0.29
    pers
    0.27
    åĤ¬çĶŁ
    0.25
    ets
    0.25
    åĩłä¹İæīĢæľī
    0.25
    å¸Ń
    0.25
    æĮ¤
    0.24
    åIJİåĨį
    0.24
    设
    0.24
    Activations Density 0.009%

    No Known Activations